Authors: Xiaoyan Xing, Philipp Henzler, Junhwa Hur, Runze Li, Jonathan T. Barron, Pratul P. Srinivasan, Dor Verbin
Abstract: We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require solving under-determined or ill-conditioned inverse rendering problems, and are as such unable to produce high-quality results on complex real-world scenes. Though recent progress in using generative image and video diffusion models for relighting has been promising, these techniques are either limited to 2D image and video relighting or 3D relighting of individual objects. Our approach enables controllable 3D relighting of room-scale scenes by distilling the outputs of a video-to-video relighting diffusion model into a 3D reconstruction. This side-steps the need to solve a difficult inverse rendering problem, and results in a flexible system that can relight 3D reconstructions of complex real-world scenes. We validate our approach on both synthetic and real-world datasets to show that it can faithfully render novel views of scenes under new lighting conditions.
Authors: Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, Jong Chul Ye, Duygu Ceylan, Hyeonho Jeong
Abstract: Recent foundational video-to-video diffusion models have achieved impressive results in editing user provided videos by modifying appearance, motion, or camera movement. However, real-world video editing is often an iterative process, where users refine results across multiple rounds of interaction. In this multi-turn setting, current video editors struggle to maintain cross-consistency across sequential edits. In this work, we tackle, for the first time, the problem of cross-consistency in multi-turn video editing and introduce Memory-V2V, a simple, yet effective framework that augments existing video-to-video models with explicit memory. Given an external cache of previously edited videos, Memory-V2V employs accurate retrieval and dynamic tokenization strategies to condition the current editing step on prior results. To further mitigate redundancy and computational overhead, we propose a learnable token compressor within the DiT backbone that compresses redundant conditioning tokens while preserving essential visual cues, achieving an overall speedup of 30%. We validate Memory-V2V on challenging tasks including video novel view synthesis and text-conditioned long video editing. Extensive experiments show that Memory-V2V produces videos that are significantly more cross-consistent with minimal computational overhead, while maintaining or even improving task-specific performance over state-of-the-art baselines. Project page: https://dohunlee1.github.io/MemoryV2V
Authors: Abhijeet Parida, Antonia Alomar, Zhifan Jiang, Pooneh Roshanitabrizi, Austin Tapp, Ziyue Xu, Syed Muhammad Anwar, Maria J. Ledesma-Carbayo, Holger R. Roth, Marius George Linguraru
Abstract: Federated learning enables collaborative model training across geographically distributed medical centers while preserving data privacy. However, domain shifts and heterogeneity in data often lead to a degradation in model performance. Medical imaging applications are particularly affected by variations in acquisition protocols, scanner types, and patient populations. To address these issues, we introduce Federated Template and Task Learning (FeTTL), a novel framework designed to harmonize multi-institutional medical imaging data in federated environments. FeTTL learns a global template together with a task model to align data distributions among clients. We evaluated FeTTL on two challenging and diverse multi-institutional medical imaging tasks: retinal fundus optical disc segmentation and histopathological metastasis classification. Experimental results show that FeTTL significantly outperforms the state-of-the-art federated learning baselines (p-values <0.002) for optical disc segmentation and classification of metastases from multi-institutional data. Our experiments further highlight the importance of jointly learning the template and the task. These findings suggest that FeTTL offers a principled and extensible solution for mitigating distribution shifts in federated learning, supporting robust model deployment in real-world, multi-institutional environments.
Authors: Aditya K Surikuchi, Raquel Fern\'andez, Sandro Pezzelle
Abstract: Foundation models are used for many real-world applications involving language generation from temporally-ordered multimodal events. In this work, we study the ability of models to identify the most important sub-events in a video, which is a fundamental prerequisite for narrating or summarizing multimodal events. Specifically, we focus on football games and evaluate models on their ability to distinguish between important and non-important sub-events in a game. To this end, we construct a new dataset by leveraging human preferences for importance implicit in football game highlight reels, without any additional annotation costs. Using our dataset, which we will publicly release to the community, we compare several state-of-the-art multimodal models and show that they are not far from chance level performance. Analyses of models beyond standard evaluation metrics reveal their tendency to rely on a single dominant modality and their ineffectiveness in synthesizing necessary information from multiple sources. Our findings underline the importance of modular architectures that can handle sample-level heterogeneity in multimodal data and the need for complementary training procedures that can maximize cross-modal synergy.
Authors: Aline Sindel, Andreas Maier, Vincent Christlein
Abstract: Art technological investigations of historical panel paintings rely on acquiring multi-modal image data, including visual light photography, infrared reflectography, ultraviolet fluorescence photography, x-radiography, and macro photography. For a comprehensive analysis, the multi-modal images require pixel-wise alignment, which is still often performed manually. Multi-modal image registration can reduce this laborious manual work, is substantially faster, and enables higher precision. Due to varying image resolutions, huge image sizes, non-rigid distortions, and modality-dependent image content, registration is challenging. Therefore, we propose a coarse-to-fine non-rigid multi-modal registration method efficiently relying on sparse keypoints and thin-plate-splines. Historical paintings exhibit a fine crack pattern, called craquelure, on the paint layer, which is captured by all image systems and is well-suited as a feature for registration. In our one-stage non-rigid registration approach, we employ a convolutional neural network for joint keypoint detection and description based on the craquelure and a graph neural network for descriptor matching in a patch-based manner, and filter matches based on homography reprojection errors in local areas. For coarse-to-fine registration, we introduce a novel multi-level keypoint refinement approach to register mixed-resolution images up to the highest resolution. We created a multi-modal dataset of panel paintings with a high number of keypoint annotations, and a large test set comprising five multi-modal domains and varying image resolutions. The ablation study demonstrates the effectiveness of all modules of our refinement method. Our proposed approaches achieve the best registration results compared to competing keypoint and dense matching methods and refinement methods.
Authors: Bridget Leonard, Scott O. Murray
Abstract: Multimodal language models (MLMs) perform well on semantic vision-language tasks but fail at spatial reasoning that requires adopting another agent's visual perspective. These errors reflect a persistent egocentric bias and raise questions about whether current models support allocentric reasoning. Inspired by human spatial cognition, we introduce perspective tokens, specialized embeddings that encode orientation through either (1) embodied body-keypoint cues or (2) abstract representations supporting mental rotation. Integrating these tokens into LLaVA-1.5-13B yields performance on level-2 visual perspective-taking tasks. Across synthetic and naturalistic benchmarks (Isle Bricks V2, COCO, 3DSRBench), perspective tokens improve accuracy, with rotation-based tokens generalizing to non-human reference agents. Representational analyses reveal that fine-tuning enhances latent orientation sensitivity already present in the base model, suggesting that MLMs contain precursors of allocentric reasoning but lack appropriate internal structure. Overall, embedding cognitively grounded spatial structure directly into token space provides a lightweight, model-agnostic mechanism for perspective-taking and more human-like spatial reasoning.
Authors: Yuxin Jiang, Yunkang Cao, Yuqi Cheng, Yiheng Zhang, Weiming Shen
Abstract: Few-Shot Anomaly Detection (FSAD) has emerged as a critical paradigm for identifying irregularities using scarce normal references. While recent methods have integrated textual semantics to complement visual data, they predominantly rely on features pre-trained on natural scenes, thereby neglecting the granular, domain-specific semantics essential for industrial inspection. Furthermore, prevalent fusion strategies often resort to superficial concatenation, failing to address the inherent semantic misalignment between visual and textual modalities, which compromises robustness against cross-modal interference. To bridge these gaps, this study proposes VTFusion, a vision-text multimodal fusion framework tailored for FSAD. The framework rests on two core designs. First, adaptive feature extractors for both image and text modalities are introduced to learn task-specific representations, bridging the domain gap between pre-trained models and industrial data; this is further augmented by generating diverse synthetic anomalies to enhance feature discriminability. Second, a dedicated multimodal prediction fusion module is developed, comprising a fusion block that facilitates rich cross-modal information exchange and a segmentation network that generates refined pixel-level anomaly maps under multimodal guidance. VTFusion significantly advances FSAD performance, achieving image-level AUROCs of 96.8% and 86.2% in the 2-shot scenario on the MVTec AD and VisA datasets, respectively. Furthermore, VTFusion achieves an AUPRO of 93.5% on a real-world dataset of industrial automotive plastic parts introduced in this paper, further demonstrating its practical applicability in demanding industrial scenarios.
Authors: Yihao Wang, Jusheng Zhang, Ziyi Tang, Keze Wang, Meng Yang
Abstract: Referring Expression Segmentation (RES) is a core vision-language segmentation task that enables pixel-level understanding of targets via free-form linguistic expressions, supporting critical applications such as human-robot interaction and augmented reality. Despite the progress of Multimodal Large Language Model (MLLM)-based approaches, existing RES methods still suffer from two key limitations: first, the coarse bounding boxes from MLLMs lead to redundant or non-discriminative point prompts; second, the prevalent reliance on textual coordinate reasoning is unreliable, as it fails to distinguish targets from visually similar distractors. To address these issues, we propose \textbf{\model}, a novel RES framework integrating \textbf{E}ntropy-\textbf{B}ased Point \textbf{D}iscovery (\textbf{EBD}) and \textbf{V}ision-\textbf{B}ased \textbf{R}easoning (\textbf{VBR}). Specifically, EBD identifies high-information candidate points by modeling spatial uncertainty within coarse bounding boxes, treating point selection as an information maximization process. VBR verifies point correctness through joint visual-semantic alignment, abandoning text-only coordinate inference for more robust validation. Built on these components, \model implements a coarse-to-fine workflow: bounding box initialization, entropy-guided point discovery, vision-based validation, and mask decoding. Extensive evaluations on four benchmark datasets (RefCOCO, RefCOCO+, RefCOCOg, and ReasonSeg) demonstrate that \model achieves new state-of-the-art performance across all four benchmarks, highlighting its effectiveness in generating accurate and semantically grounded segmentation masks with minimal prompts.
Authors: Chunwei Tian, Chengyuan Zhang, Bob Zhang, Zhiwu Li, C. L. Philip Chen, David Zhang
Abstract: Deep convolutional neural networks can use hierarchical information to progressively extract structural information to recover high-quality images. However, preserving the effectiveness of the obtained structural information is important in image super-resolution. In this paper, we propose a cosine network for image super-resolution (CSRNet) by improving a network architecture and optimizing the training strategy. To extract complementary homologous structural information, odd and even heterogeneous blocks are designed to enlarge the architectural differences and improve the performance of image super-resolution. Combining linear and non-linear structural information can overcome the drawback of homologous information and enhance the robustness of the obtained structural information in image super-resolution. Taking into account the local minimum of gradient descent, a cosine annealing mechanism is used to optimize the training procedure by performing warm restarts and adjusting the learning rate. Experimental results illustrate that the proposed CSRNet is competitive with state-of-the-art methods in image super-resolution.
Authors: Shuying Li, Qiang Ma, San Zhang, Chuang Yang
Abstract: Infrared small target detection (IRSTD) is critical for applications like remote sensing and surveillance, which aims to identify small, low-contrast targets against complex backgrounds. However, existing methods often struggle with inadequate joint modeling of local-global features (harming target-background discrimination) or feature redundancy and semantic dilution (degrading target representation quality). To tackle these issues, we propose DCCS-Det (Directional Context and Cross-Scale Aware Detector for Infrared Small Target), a novel detector that incorporates a Dual-stream Saliency Enhancement (DSE) block and a Latent-aware Semantic Extraction and Aggregation (LaSEA) module. The DSE block integrates localized perception with direction-aware context aggregation to help capture long-range spatial dependencies and local details. On this basis, the LaSEA module mitigates feature degradation via cross-scale feature extraction and random pooling sampling strategies, enhancing discriminative features and suppressing noise. Extensive experiments show that DCCS-Det achieves state-of-the-art detection accuracy with competitive efficiency across multiple datasets. Ablation studies further validate the contributions of DSE and LaSEA in improving target perception and feature representation under complex scenarios. \href{https://huggingface.co/InPeerReview/InfraredSmallTargetDetection-IRSTD.DCCS}{DCCS-Det Official Code is Available Here!}
URLs: https://huggingface.co/InPeerReview/InfraredSmallTargetDetection-IRSTD.DCCS
Authors: Jongmin Yu, Hyeontaek Oh, Zhongtian Sun, Angelica I Aviles-Rivero, Moongu Jeon, Jinhong Yang
Abstract: Existing face-swapping methods often deliver competitive results in constrained settings but exhibit substantial quality degradation when handling extreme facial poses. To improve facial pose robustness, explicit geometric features are applied, but this approach remains problematic since it introduces additional dependencies and increases computational cost. Diffusion-based methods have achieved remarkable results; however, they are impractical for real-time processing. We introduce AlphaFace, which leverages an open-source vision-language model and CLIP image and text embeddings to apply novel visual and textual semantic contrastive losses. AlphaFace enables stronger identity representation and more precise attribute preservation, all while maintaining real-time performance. Comprehensive experiments across FF++, MPIE, and LPFF demonstrate that AlphaFace surpasses state-of-the-art methods in pose-challenging cases. The project is publicly available on `https://github.com/andrewyu90/Alphaface_Official.git'.
URLs: https://github.com/andrewyu90/Alphaface_Official.git'.
Authors: Shuying Li, Qiang Ma, San Zhang, Wuwei Wang, Chuang Yang
Abstract: Infrared small target detection (IRSTD) plays a crucial role in numerous military and civilian applications. However, existing methods often face the gradual degradation of target edge pixels as the number of network layers increases, and traditional convolution struggles to differentiate between frequency components during feature extraction, leading to low-frequency backgrounds interfering with high-frequency targets and high-frequency noise triggering false detections. To address these limitations, we propose MDAFNet (Multi-scale Differential Edge and Adaptive Frequency Guided Network for Infrared Small Target Detection), which integrates the Multi-Scale Differential Edge (MSDE) module and Dual-Domain Adaptive Feature Enhancement (DAFE) module. The MSDE module, through a multi-scale edge extraction and enhancement mechanism, effectively compensates for the cumulative loss of target edge information during downsampling. The DAFE module combines frequency domain processing mechanisms with simulated frequency decomposition and fusion mechanisms in the spatial domain to effectively improve the network's capability to adaptively enhance high-frequency targets and selectively suppress high-frequency noise. Experimental results on multiple datasets demonstrate the superior detection performance of MDAFNet.
Authors: Bo Zhang, Ming Zhang, Kun Wu, Lei Bian, Yi Lin
Abstract: Erratum to the paper (Zhang et al., 2025): corrections to Table IV and the data in Page 3, Section A. In the post-pandemic era, a high proportion of civil aviation passengers wear masks during security checks, posing significant challenges to traditional face recognition models. The backbone network serves as the core component of face recognition models. In standard tests, r100 series models excelled (98%+ accuracy at 0.01% FAR in face comparison, high top1/top5 in search). r50 ranked second, r34_mask_v1 lagged. In masked tests, r100_mask_v2 led (90.07% accuracy), r50_mask_v3 performed best among r50 but trailed r100. Vit-Small/Tiny showed strong masked performance with gains in effectiveness. Through extensive comparative experiments, this paper conducts a comprehensive evaluation of several core backbone networks, aiming to reveal the impacts of different models on face recognition with and without masks, and provide specific deployment recommendations.
Authors: Xiaojiang Peng, Jingyi Chen, Zebang Cheng, Bao Peng, Fengyi Wu, Yifei Dong, Shuyuan Tu, Qiyu Hu, Huiting Huang, Yuxiang Lin, Jun-Yan He, Kai Wang, Zheng Lian, Zhi-Qi Cheng
Abstract: Understanding human emotions from multimodal signals poses a significant challenge in affective computing and human-robot interaction. While multimodal large language models (MLLMs) have excelled in general vision-language tasks, their capabilities in emotional reasoning remain limited. The field currently suffers from a scarcity of large-scale datasets with high-quality, descriptive emotion annotations and lacks standardized benchmarks for evaluation. Our preliminary framework, Emotion-LLaMA, pioneered instruction-tuned multimodal learning for emotion reasoning but was restricted by explicit face detectors, implicit fusion strategies, and low-quality training data with limited scale. To address these limitations, we present Emotion-LLaMAv2 and the MMEVerse benchmark, establishing an end-to-end pipeline together with a standardized evaluation setting for emotion recognition and reasoning. Emotion-LLaMAv2 introduces three key advances. First, an end-to-end multiview encoder eliminates external face detection and captures nuanced emotional cues via richer spatial and temporal multiview tokens. Second, a Conv Attention pre-fusion module is designed to enable simultaneous local and global multimodal feature interactions external to the LLM backbone. Third, a perception-to-cognition curriculum instruction tuning scheme within the LLaMA2 backbone unifies emotion recognition and free-form emotion reasoning. To support large-scale training and reproducible evaluation, MMEVerse aggregates twelve publicly available emotion datasets, including IEMOCAP, MELD, DFEW, and MAFW, into a unified multimodal instruction format. The data are re-annotated via a multi-agent pipeline involving Qwen2 Audio, Qwen2.5 VL, and GPT 4o, producing 130k training clips and 36k testing clips across 18 evaluation benchmarks.
Authors: Peixian Liang, Songhao Li, Shunsuke Koga, Yutong Li, Zahra Alipour, Yucheng Tang, Daguang Xu, Zhi Huang
Abstract: Accurate semantic segmentation for histopathology image is crucial for quantitative tissue analysis and downstream clinical modeling. Recent segmentation foundation models have improved generalization through large-scale pretraining, yet remain poorly aligned with pathology because they treat segmentation as a static visual prediction task. Here we present VISTA-PATH, an interactive, class-aware pathology segmentation foundation model designed to resolve heterogeneous structures, incorporate expert feedback, and produce pixel-level segmentation that are directly meaningful for clinical interpretation. VISTA-PATH jointly conditions segmentation on visual context, semantic tissue descriptions, and optional expert-provided spatial prompts, enabling precise multi-class segmentation across heterogeneous pathology images. To support this paradigm, we curate VISTA-PATH Data, a large-scale pathology segmentation corpus comprising over 1.6 million image-mask-text triplets spanning 9 organs and 93 tissue classes. Across extensive held-out and external benchmarks, VISTA-PATH consistently outperforms existing segmentation foundation models. Importantly, VISTA-PATH supports dynamic human-in-the-loop refinement by propagating sparse, patch-level bounding-box annotation feedback into whole-slide segmentation. Finally, we show that the high-fidelity, class-aware segmentation produced by VISTA-PATH is a preferred model for computational pathology. It improve tissue microenvironment analysis through proposed Tumor Interaction Score (TIS), which exhibits strong and significant associations with patient survival. Together, these results establish VISTA-PATH as a foundation model that elevates pathology image segmentation from a static prediction to an interactive and clinically grounded representation for digital pathology. Source code and demo can be found at https://github.com/zhihuanglab/VISTA-PATH.
Authors: Meng Cao, Haoran Tang, Haoze Zhao, Mingfei Han, Ruyang Liu, Qiang Sun, Xiaojun Chang, Ian Reid, Xiaodan Liang
Abstract: Understanding the physical world, including object dynamics, material properties, and causal interactions, remains a core challenge in artificial intelligence. Although recent multi-modal large language models (MLLMs) have demonstrated impressive general reasoning capabilities, they still fall short of achieving human-level understanding of physical principles. Existing datasets for physical reasoning either rely on real-world videos, which incur high annotation costs, or on synthetic simulations, which suffer from limited realism and diversity. In this paper, we propose a novel paradigm that leverages glitches in gameplay videos, referring to visual anomalies that violate predefined physical laws, as a rich and scalable supervision source for physical world understanding. We introduce PhysGame, an meta information guided instruction-tuning dataset containing 140,057 glitch-centric question-answer pairs across five physical domains and sixteen fine-grained categories. To ensure data accuracy, we design a prompting strategy that utilizes gameplay metadata such as titles and descriptions to guide high-quality QA generation. Complementing PhysGame, we construct GameBench, an expert-annotated benchmark with 880 glitch-identified gameplay videos designed to evaluate physical reasoning capabilities. Extensive experiments show that PhysGame significantly enhances both Game2Real transferability, improving the real world physical reasoning performance of Qwen2.5VL by 2.5% on PhysBench, and Game2General transferability, yielding a 1.9% gain on the MVBench benchmark. Moreover, PhysGame-tuned models achieve a 3.7% absolute improvement on GameBench, demonstrating enhanced robustness in detecting physical implausibilities. These results indicate that learning from gameplay anomalies offers a scalable and effective pathway toward advancing physical world understanding in multimodal intelligence.
Authors: Remi Chierchia, L\'eo Lebrat, David Ahmedt-Aristizabal, Yulia Arzhaeva, Olivier Salvado, Clinton Fookes, Rodrigo Santa Cruz
Abstract: Wound care is often challenged by the economic and logistical burdens that consistently afflict patients and hospitals worldwide. In recent decades, healthcare professionals have sought support from computer vision and machine learning algorithms. In particular, wound segmentation has gained interest due to its ability to provide professionals with fast, automatic tissue assessment from standard RGB images. Some approaches have extended segmentation to 3D, enabling more complete and precise healing progress tracking. However, inferring multi-view consistent 3D structures from 2D images remains a challenge. In this paper, we evaluate WoundNeRF, a NeRF SDF-based method for estimating robust wound segmentations from automatically generated annotations. We demonstrate the potential of this paradigm in recovering accurate segmentations by comparing it against state-of-the-art Vision Transformer networks and conventional rasterisation-based algorithms. The code will be released to facilitate further development in this promising paradigm.
Authors: Chen Long, Dian Chen, Ruifei Ding, Zhe Chen, Zhen Dong, Bisheng Yang
Abstract: Accurate fine-grained tree species classification is critical for forest inventory and biodiversity monitoring. Existing methods predominantly focus on designing complex architectures to fit local data distributions. However, they often overlook the long-tailed distributions and high inter-class similarity inherent in limited data, thereby struggling to distinguish between few-shot or confusing categories. In the process of knowledge dissemination in the human world, individuals will actively seek expert assistance to transcend the limitations of local thinking. Inspired by this, we introduce an external "Domain Expert" and propose an Expert Knowledge-Guided Classification Decision Calibration Network (EKDC-Net) to overcome these challenges. Our framework addresses two core issues: expert knowledge extraction and utilization. Specifically, we first develop a Local Prior Guided Knowledge Extraction Module (LPKEM). By leveraging Class Activation Map (CAM) analysis, LPKEM guides the domain expert to focus exclusively on discriminative features essential for classification. Subsequently, to effectively integrate this knowledge, we design an Uncertainty-Guided Decision Calibration Module (UDCM). This module dynamically corrects the local model's decisions by considering both overall category uncertainty and instance-level prediction uncertainty. Furthermore, we present a large-scale classification dataset covering 102 tree species, named CU-Tree102 to address the issue of scarce diversity in current benchmarks. Experiments on three benchmark datasets demonstrate that our approach achieves state-of-the-art performance. Crucially, as a lightweight plug-and-play module, EKDC-Net improves backbone accuracy by 6.42% and precision by 11.46% using only 0.08M additional learnable parameters. The dataset, code, and pre-trained models are available at https://github.com/WHU-USI3DV/TreeCLS.
Authors: Tongcheng Fang, Hanling Zhang, Ruiqi Xie, Zhuo Han, Xin Tao, Tianchen Zhao, Pengfei Wan, Wenbo Ding, Wanli Ouyang, Xuefei Ning, Yu Wang
Abstract: Diffusion Transformers have recently demonstrated remarkable performance in video generation. However, the long input sequences result in high computational latency due to the quadratic complexity of full attention. Various sparse attention mechanisms have been proposed. Training-free sparse attention is constrained by limited sparsity and thus offers modest acceleration, whereas training-based methods can reach much higher sparsity but demand substantial data and computation for training. In this work, we propose SALAD, introducing a lightweight linear attention branch in parallel with the sparse attention. By incorporating an input-dependent gating mechanism to finely balance the two branches, our method attains 90% sparsity and 1.72x inference speedup, while maintaining generation quality comparable to the full attention baseline. Moreover, our finetuning process is highly efficient, requiring only 2,000 video samples and 1,600 training steps with a batch size of 8.
Authors: Daixian Liu, Jiayi Kuang, Yinghui Li, Yangning Li, Di Yin, Haoyu Cao, Xing Sun, Ying Shen, Hai-Tao Zheng, Liang Lin, Philip S. Yu
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual recognition and semantic understanding. Nevertheless, their ability to perform precise compositional spatial reasoning remains largely unexplored. Existing benchmarks often involve relatively simple tasks and rely on semantic approximations or coarse relative positioning, while their evaluation metrics are typically limited and lack rigorous mathematical formulations. To bridge this gap, we introduce TangramPuzzle, a geometry-grounded benchmark designed to evaluate compositional spatial reasoning through the lens of the classic Tangram game. We propose the Tangram Construction Expression (TCE), a symbolic geometric framework that grounds tangram assemblies in exact, machine-verifiable coordinate specifications, to mitigate the ambiguity of visual approximation. We design two complementary tasks: Outline Prediction, which demands inferring global shapes from local components, and End-to-End Code Generation, which requires solving inverse geometric assembly problems. We conduct extensive evaluation experiments on advanced open-source and proprietary models, revealing an interesting insight: MLLMs tend to prioritize matching the target silhouette while neglecting geometric constraints, leading to distortions or deformations of the pieces.
Authors: Runmao Yao, Junsheng Zhou, Zhen Dong, Yu-Shen Liu
Abstract: Single-view indoor scene generation plays a crucial role in a range of real-world applications. However, generating a complete 360{\deg} scene from a single image remains a highly ill-posed and challenging problem. Recent approaches have made progress by leveraging diffusion models and depth estimation networks, yet they still struggle to maintain appearance consistency and geometric plausibility under large viewpoint changes, limiting their effectiveness in full-scene generation. To address this, we propose AnchoredDream, a novel zero-shot pipeline that anchors 360{\deg} scene generation on high-fidelity geometry via an appearance-geometry mutual boosting mechanism. Given a single-view image, our method first performs appearance-guided geometry generation to construct a reliable 3D scene layout. Then, we progressively generate the complete scene through a series of modules: warp-and-inpaint, warp-and-refine, post-optimization, and a novel Grouting Block, which ensures seamless transitions between the input view and generated regions. Extensive experiments demonstrate that AnchoredDream outperforms existing methods by a large margin in both appearance consistency and geometric plausibility--all in a zero-shot manner. Our results highlight the potential of geometric grounding for high-quality, zero-shot single-view scene generation.
Authors: Zixian Liu, Zhaoxi Chen, Liang Pan, Ziwei Liu
Abstract: In recent years, researchers have increasingly been interested in how to enable Multimodal Large Language Models (MLLM) to possess spatial understanding and reasoning capabilities. However, most existing methods overlook the importance of the ability to continuously work in an ever-changing world, and lack the possibility of deployment on embodied systems in real-world environments. In this work, we introduce OnlineSI, a framework that can continuously improve its spatial understanding of its surroundings given a video stream. Our core idea is to maintain a finite spatial memory to retain past observations, ensuring the computation required for each inference does not increase as the input accumulates. We further integrate 3D point cloud information with semantic information, helping MLLM to better locate and identify objects in the scene. To evaluate our method, we introduce the Fuzzy $F_1$-Score to mitigate ambiguity, and test our method on two representative datasets. Experiments demonstrate the effectiveness of our method, paving the way towards real-world embodied systems.
Authors: Erik Wallin, Fredrik Kahl, Lars Hammarstrand
Abstract: Hierarchical open-set classification handles previously unseen classes by assigning them to the most appropriate high-level category in a class taxonomy. We extend this paradigm to the semi-supervised setting, enabling the use of large-scale, uncurated datasets containing a mixture of known and unknown classes to improve the hierarchical open-set performance. To this end, we propose a teacher-student framework based on pseudo-labeling. Two key components are introduced: 1) subtree pseudo-labels, which provide reliable supervision in the presence of unknown data, and 2) age-gating, a mechanism that mitigates overconfidence in pseudo-labels. Experiments show that our framework outperforms self-supervised pretraining followed by supervised adaptation, and even matches the fully supervised counterpart when using only 20 labeled samples per class on the iNaturalist19 benchmark. Our code is available at https://github.com/walline/semihoc.
Authors: Shuying Li, Yuchen Wang, San Zhang, Chuang Yang
Abstract: Remote sensing change detection (RSCD) aims to identify the spatio-temporal changes of land cover, providing critical support for multi-disciplinary applications (e.g., environmental monitoring, disaster assessment, and climate change studies). Existing methods focus either on extracting features from localized patches, or pursue processing entire images holistically, which leads to the cross temporal feature matching deviation and exhibiting sensitivity to radiometric and geometric noise. Following the above issues, we propose a dual-module collaboration guided hierarchical adaptive aggregation framework, namely HA2F, which consists of dynamic hierarchical feature calibration module (DHFCM) and noise-adaptive feature refinement module (NAFRM). The former dynamically fuses adjacent-level features through perceptual feature selection, suppressing irrelevant discrepancies to address multi-temporal feature alignment deviations. The NAFRM utilizes the dual feature selection mechanism to highlight the change sensitive regions and generate spatial masks, suppressing the interference of irrelevant regions or shadows. Extensive experiments verify the effectiveness of the proposed HA2F, which achieves state-of-the-art performance on LEVIR-CD, WHU-CD, and SYSU-CD datasets, surpassing existing comparative methods in terms of both precision metrics and computational efficiency. In addition, ablation experiments show that DHFCM and NAFRM are effective. \href{https://huggingface.co/InPeerReview/RemoteSensingChangeDetection-RSCD.HA2F}{HA2F Official Code is Available Here!}
URLs: https://huggingface.co/InPeerReview/RemoteSensingChangeDetection-RSCD.HA2F
Authors: Yuqian Zheng, Mariana-Iuliana Georgescu
Abstract: Composed Video Retrieval (CoVR) facilitates video retrieval by combining visual and textual queries. However, existing CoVR frameworks typically fuse multimodal inputs in a single stage, achieving only marginal gains over initial baseline. To address this, we propose a novel CoVR framework that leverages the representational power of Vision Language Models (VLMs). Our framework incorporates a novel cross-attention module X-Aligner, composed of cross-attention layers that progressively fuse visual and textual inputs and align their multimodal representation with that of the target video. To further enhance the representation of the multimodal query, we incorporate the caption of the visual query as an additional input. The framework is trained in two stages to preserve the pretrained VLM representation. In the first stage, only the newly introduced module is trained, while in the second stage, the textual query encoder is also fine-tuned. We implement our framework on top of BLIP-family architecture, namely BLIP and BLIP-2, and train it on the Webvid-CoVR data set. In addition to in-domain evaluation on Webvid-CoVR-Test, we perform zero-shot evaluations on the Composed Image Retrieval (CIR) data sets CIRCO and Fashion-IQ. Our framework achieves state-of-the-art performance on CoVR obtaining a Recall@1 of 63.93% on Webvid-CoVR-Test, and demonstrates strong zero-shot generalization on CIR tasks.
Authors: Jingsong Xia, Siqi Wang
Abstract: Intelligent medical image analysis is essential for clinical decision support but is often limited by scarce annotations, constrained computational resources, and suboptimal model generalization. To address these challenges, we propose a lightweight medical image classification framework that integrates self-supervised contrastive learning with quantum-enhanced feature modeling. MobileNetV2 is employed as a compact backbone and pretrained using a SimCLR-style self-supervised paradigm on unlabeled images. A lightweight parameterized quantum circuit (PQC) is embedded as a quantum feature enhancement module, forming a hybrid classical-quantum architecture, which is subsequently fine-tuned on limited labeled data. Experimental results demonstrate that, with only approximately 2-3 million parameters and low computational cost, the proposed method consistently outperforms classical baselines without self-supervised learning or quantum enhancement in terms of Accuracy, AUC, and F1-score. Feature visualization further indicates improved discriminability and representation stability. Overall, this work provides a practical and forward-looking solution for high-performance medical artificial intelligence under resource-constrained settings.
Authors: Rongxin Huang, Guangfeng Lin, Wenbo Zhou, Zhirong Li, Wenhuan Wu
Abstract: Unmanned Aerial Vehicle (UAV) applications have become increasingly prevalent in aerial photography and object recognition. However, there are major challenges to accurately capturing small targets in object detection due to the imbalanced scale and the blurred edges. To address these issues, boundary and position information mining (BPIM) framework is proposed for capturing object edge and location cues. The proposed BPIM includes position information guidance (PIG) module for obtaining location information, boundary information guidance (BIG) module for extracting object edge, cross scale fusion (CSF) module for gradually assembling the shallow layer image feature, three feature fusion (TFF) module for progressively combining position and boundary information, and adaptive weight fusion (AWF) module for flexibly merging the deep layer semantic feature. Therefore, BPIM can integrate boundary, position, and scale information in image for small object detection using attention mechanisms and cross-scale feature fusion strategies. Furthermore, BPIM not only improves the discrimination of the contextual feature by adaptive weight fusion with boundary, but also enhances small object perceptions by cross-scale position fusion. On the VisDrone2021, DOTA1.0, and WiderPerson datasets, experimental results show the better performances of BPIM compared to the baseline Yolov5-P2, and obtains the promising performance in the state-of-the-art methods with comparable computation load.
Authors: Ananya Kadali, Sunnie Jehan-Morrison, Orasiki Wellington, Barney Evans, Precious Durojaiye, Richard Guest
Abstract: The growing demand for diverse and high-quality facial datasets for training and testing biometric systems is challenged by privacy regulations, data scarcity, and ethical concerns. Synthetic facial images offer a potential solution, yet existing generative models often struggle to balance realism, diversity, and identity preservation. This paper presents SCHIGAND, a novel synthetic face generation pipeline integrating StyleCLIP, HyperStyle, InterfaceGAN, and Diffusion models to produce highly realistic and controllable facial datasets. SCHIGAND enhances identity preservation while generating realistic intra-class variations and maintaining inter-class distinctiveness, making it suitable for biometric testing. The generated datasets were evaluated using ArcFace, a leading facial verification model, to assess their effectiveness in comparison to real-world facial datasets. Experimental results demonstrate that SCHIGAND achieves a balance between image quality and diversity, addressing key limitations of prior generative models. This research highlights the potential of SCHIGAND to supplement and, in some cases, replace real data for facial biometric applications, paving the way for privacy-compliant and scalable solutions in synthetic dataset generation.
Authors: Minsu Gong, Nuri Ryu, Jungseul Ok, Sunghyun Cho
Abstract: Recent advances in image editing leverage latent diffusion models (LDMs) for versatile, text-prompt-driven edits across diverse tasks. Yet, maintaining pixel-level edge structures-crucial for tasks such as photorealistic style transfer or image tone adjustment-remains as a challenge for latent-diffusion-based editing. To overcome this limitation, we propose a novel Structure Preservation Loss (SPL) that leverages local linear models to quantify structural differences between input and edited images. Our training-free approach integrates SPL directly into the diffusion model's generative process to ensure structural fidelity. This core mechanism is complemented by a post-processing step to mitigate LDM decoding distortions, a masking strategy for precise edit localization, and a color preservation loss to preserve hues in unedited areas. Experiments confirm SPL enhances structural fidelity, delivering state-of-the-art performance in latent-diffusion-based image editing. Our code will be publicly released at https://github.com/gongms00/SPL.
Authors: Aurora Pia Ghiardelli, Guangzhi Tang, Tao Sun
Abstract: We propose a reliable and energy-efficient framework for 3D brain tumor segmentation using spiking neural networks (SNNs). A multi-view ensemble of sagittal, coronal, and axial SNN models provides voxel-wise uncertainty estimation and enhances segmentation robustness. To address the high computational cost in training SNN models for semantic image segmentation, we employ Forward Propagation Through Time (FPTT), which maintains temporal learning efficiency with significantly reduced computational cost. Experiments on the Multimodal Brain Tumor Segmentation Challenges (BraTS 2017 and BraTS 2023) demonstrate competitive accuracy, well-calibrated uncertainty, and an 87% reduction in FLOPs, underscoring the potential of SNNs for reliable, low-power medical IoT and Point-of-Care systems.
Authors: Ming Li, Hui Shan, Kai Zheng, Chentao Shen, Siyu Liu, Yanwei Fu, Zhen Chen, Xiangru Huang
Abstract: High-quality 3D garment reconstruction plays a crucial role in mitigating the sim-to-real gap in applications such as digital avatars, virtual try-on and robotic manipulation. However, existing garment reconstruction methods typically rely on unstructured representations, such as 3D Gaussian Splats, struggling to provide accurate reconstructions of garment topology and sewing structures. As a result, the reconstructed outputs are often unsuitable for high-fidelity physical simulation. We propose ReWeaver, a novel framework for topology-accurate 3D garment and sewing pattern reconstruction from sparse multi-view RGB images. Given as few as four input views, ReWeaver predicts seams and panels as well as their connectivities in both the 2D UV space and the 3D space. The predicted seams and panels align precisely with the multi-view images, yielding structured 2D--3D garment representations suitable for 3D perception, high-fidelity physical simulation, and robotic manipulation. To enable effective training, we construct a large-scale dataset GCD-TS, comprising multi-view RGB images, 3D garment geometries, textured human body meshes and annotated sewing patterns. The dataset contains over 100,000 synthetic samples covering a wide range of complex geometries and topologies. Extensive experiments show that ReWeaver consistently outperforms existing methods in terms of topology accuracy, geometry alignment and seam-panel consistency.
Authors: Hongda Liu, Yunfan Liu, Min Ren, Lin Sui, Yunlong Wang, Zhenan Sun
Abstract: In skeleton-based human activity understanding, existing methods often adopt the contrastive learning paradigm to construct a discriminative feature space. However, many of these approaches fail to exploit the structural inter-class similarities and overlook the impact of anomalous positive samples. In this study, we introduce ACLNet, an Affinity Contrastive Learning Network that explores the intricate clustering relationships among human activity classes to improve feature discrimination. Specifically, we propose an affinity metric to refine similarity measurements, thereby forming activity superclasses that provide more informative contrastive signals. A dynamic temperature schedule is also introduced to adaptively adjust the penalty strength for various superclasses. In addition, we employ a margin-based contrastive strategy to improve the separation of hard positive and negative samples within classes. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, Kinetics-Skeleton, PKU-MMD, FineGYM, and CASIA-B demonstrate the superiority of our method in skeleton-based action recognition, gait recognition, and person re-identification. The source code is available at https://github.com/firework8/ACLNet.
Authors: Sana Al-azzawi, Elisa Barney, Marcus Liwicki
Abstract: Handwritten text recognition (HTR) for Arabic-script languages still lags behind Latin-script HTR, despite recent advances in model architectures, datasets, and benchmarks. We show that data quality is a significant limiting factor in many published datasets and propose CER-HV (CER-based Ranking with Human Verification) as a framework to detect and clean label errors. CER-HV combines a CER-based noise detector, built on a carefully configured Convolutional Recurrent Neural Network (CRNN) with early stopping to avoid overfitting noisy samples, and a human-in-the-loop (HITL) step that verifies high-ranking samples. The framework reveals that several existing datasets contain previously underreported problems, including transcription, segmentation, orientation, and non-text content errors. These have been identified with up to 90 percent precision in the Muharaf and 80-86 percent in the PHTI datasets. We also show that our CRNN achieves state-of-the-art performance across five of the six evaluated datasets, reaching 8.45 percent Character Error Rate (CER) on KHATT (Arabic), 8.26 percent on PHTI (Pashto), 10.66 percent on Ajami, and 10.11 percent on Muharaf (Arabic), all without any data cleaning. We establish a new baseline of 11.3 percent CER on the PHTD (Persian) dataset. Applying CER-HV improves the evaluation CER by 0.3-0.6 percent on the cleaner datasets and 1.0-1.8 percent on the noisier ones. Although our experiments focus on documents written in an Arabic-script language, including Arabic, Persian, Urdu, Ajami, and Pashto, the framework is general and can be applied to other text recognition datasets.
Authors: Yann Le Gall, Nicolas Burlet, Mathieu Simon, Fabien Novella, Samantha Dugelay, Jean-Philippe Malkasse
Abstract: Circular Synthetic Aperture Sonar (CSAS) provides a 360{\deg} azimuth view of the seabed, surpassing the limited aperture and mono-view image of conventional side-scan SAS. This makes CSAS a valuable tool for target recognition in mine warfare where the diversity of point of view is essential for reducing false alarms. CSAS processing typically produces a very high-resolution two-dimensional image. However, the parallax introduced by the circular displacement of the illuminator fill-in the shadow regions, and the shadow cast by an object on the seafloor is lost in favor of azimuth coverage and resolution. Yet the shadows provide complementary information on target shape useful for target recognition. In this paper, we explore a way to retrieve shadow information from CSAS data to improve target analysis and carry 3D reconstruction. Sub-aperture filtering is used to get a collection of images at various points of view along the circular trajectory and fixed focus shadow enhancement (FFSE) is applied to obtain sharp shadows. An interactive interface is also proposed to allow human operators to visualize these shadows along the circular trajectory. A space-carving reconstruction method is applied to infer the 3D shape of the object from the segmented shadows. The results demonstrate the potential of shadows in circular SAS for improving target analysis and 3D reconstruction.
Authors: Renjie Ding, Yaonan Wang, Min Liu, Jialin Zhu, Jiazheng Wang, Jiahao Zhao, Wenting Shen, Feixiang He, Xiang Che
Abstract: 3D Gaussian Splatting (3DGS) has emerged as a powerful technique for real-time novel view synthesis. As an explicit representation optimized through gradient propagation among primitives, optimization widely accepted in deep neural networks (DNNs) is actually adopted in 3DGS, such as synchronous weight updating and Adam with the adaptive gradient. However, considering the physical significance and specific design in 3DGS, there are two overlooked details in the optimization of 3DGS: (i) update step coupling, which induces optimizer state rescaling and costly attribute updates outside the viewpoints, and (ii) gradient coupling in the moment, which may lead to under- or over-effective regularization. Nevertheless, such a complex coupling is under-explored. After revisiting the optimization of 3DGS, we take a step to decouple it and recompose the process into: Sparse Adam, Re-State Regularization and Decoupled Attribute Regularization. Taking a large number of experiments under the 3DGS and 3DGS-MCMC frameworks, our work provides a deeper understanding of these components. Finally, based on the empirical analysis, we re-design the optimization and propose AdamW-GS by re-coupling the beneficial components, under which better optimization efficiency and representation effectiveness are achieved simultaneously.
Authors: Steffen Knoblauch, Ram Kumar Muthusamy, Pedram Ghamisi, Alexander Zipf
Abstract: Highway networks are crucial for economic prosperity. Climate change-induced temperature fluctuations are exacerbating stress on road pavements, resulting in elevated maintenance costs. This underscores the need for targeted and efficient maintenance strategies. This study investigates the potential of open-source data to guide highway infrastructure maintenance. The proposed framework integrates airborne imagery and OpenStreetMap (OSM) to fine-tune YOLOv11 for highway crack localization. To demonstrate the framework's real-world applicability, a Swiss Relative Highway Crack Density (RHCD) index was calculated to inform nationwide highway maintenance. The crack classification model achieved an F1-score of $0.84$ for the positive class (crack) and $0.97$ for the negative class (no crack). The Swiss RHCD index exhibited weak correlations with Long-term Land Surface Temperature Amplitudes (LT-LST-A) (Pearson's $r\ = -0.05$) and Traffic Volume (TV) (Pearson's $r\ = 0.17$), underlining the added value of this novel index for guiding maintenance over other data. Significantly high RHCD values were observed near urban centers and intersections, providing contextual validation for the predictions. These findings highlight the value of open-source data sharing to drive innovation, ultimately enabling more efficient solutions in the public sector.
Authors: Alda Jo\~ao Andrade, M\'onica Martins, Andr\'e Ferreira, Tarc\'isio Ara\'ujo, Lu\'is Lopes, Victor Alves
Abstract: Endoscopic Retrograde Cholangiopancreatography (ERCP) is a key procedure in the diagnosis and treatment of biliary and pancreatic diseases. Artificial intelligence has been pointed as one solution to automatize diagnosis. However, public ERCP datasets are scarce, which limits the use of such approach. Therefore, this study aims to help fill this gap by providing a large and curated dataset. The collection is composed of 19.018 raw images and 19.317 processed from 1.602 patients. 5.519 images are labeled, which provides a ready to use dataset. All images were manually inspected and annotated by two gastroenterologist with more than 5 years of experience and reviewed by another gastroenterologist with more than 20 years of experience, all with more than 400 ERCP procedures annually. The utility and validity of the dataset is proven by a classification experiment. This collection aims to provide or contribute for a benchmark in automatic ERCP analysis and diagnosis of biliary and pancreatic diseases.
Authors: Cuong Le, Pavl\'o Melnyk, Bastian Wandt, M{\aa}rten Wadenb\"ack
Abstract: Recovering 3D human poses from a monocular camera view is a highly ill-posed problem due to the depth ambiguity. Earlier studies on 3D human pose lifting from 2D often contain incorrect-yet-overconfident 3D estimations. To mitigate the problem, emerging probabilistic approaches treat the 3D estimations as a distribution, taking into account the uncertainty measurement of the poses. Falling in a similar category, we proposed FMPose, a probabilistic 3D human pose estimation method based on the flow matching generative approach. Conditioned on the 2D cues, the flow matching scheme learns the optimal transport from a simple source distribution to the plausible 3D human pose distribution via continuous normalizing flows. The 2D lifting condition is modeled via graph convolutional networks, leveraging the learnable connections between human body joints as the graph structure for feature aggregation. Compared to diffusion-based methods, the FMPose with optimal transport produces faster and more accurate 3D pose generations. Experimental results show major improvements of our FMPose over current state-of-the-art methods on three common benchmarks for 3D human pose estimation, namely Human3.6M, MPI-INF-3DHP and 3DPW.
Authors: Jiahao Li, Yunpeng Bai, Yongkang Dai, Hao Guo, Hongping Gan, Yilei Shi
Abstract: Previous representation and generation approaches for the B-rep relied on graph-based representations that disentangle geometric and topological features through decoupled computational pipelines, thereby precluding the application of sequence-based generative frameworks, such as transformer architectures that have demonstrated remarkable performance. In this paper, we propose BrepARG, the first attempt to encode B-rep's geometry and topology into a holistic token sequence representation, enabling sequence-based B-rep generation with an autoregressive architecture. Specifically, BrepARG encodes B-rep into 3 types of tokens: geometry and position tokens representing geometric features, and face index tokens representing topology. Then the holistic token sequence is constructed hierarchically, starting with constructing the geometry blocks (i.e., faces and edges) using the above tokens, followed by geometry block sequencing. Finally, we assemble the holistic sequence representation for the entire B-rep. We also construct a transformer-based autoregressive model that learns the distribution over holistic token sequences via next-token prediction, using a multi-layer decoder-only architecture with causal masking. Experiments demonstrate that BrepARG achieves state-of-the-art (SOTA) performance. BrepARG validates the feasibility of representing B-rep as holistic token sequences, opening new directions for B-rep generation.
Authors: Shuai Huang, Xuhan Lin, Yuwu Lu
Abstract: Few-shot class-incremental learning (FSCIL) presents a core challenge in continual learning, requiring models to rapidly adapt to new classes with very limited samples while mitigating catastrophic forgetting. Recent prompt-based methods, which integrate pretrained backbones with task-specific prompts, have made notable progress. However, under extreme few-shot incremental settings, the model's ability to transfer and generalize becomes critical, and it is thus essential to leverage pretrained knowledge to learn feature representations that can be shared across future categories during the base session. Inspired by the mechanism of the CLS token, which is similar to human attention and progressively filters out task-irrelevant information, we propose the CLS Token Attention Steering Prompts (CASP). This approach introduces class-shared trainable bias parameters into the query, key, and value projections of the CLS token to explicitly modulate the self-attention weights. To further enhance generalization, we also design an attention perturbation strategy and perform Manifold Token Mixup in the shallow feature space, synthesizing potential new class features to improve generalization and reserve the representation capacity for upcoming tasks. Experiments on the CUB200, CIFAR100, and ImageNet-R datasets demonstrate that CASP outperforms state-of-the-art methods in both standard and fine-grained FSCIL settings without requiring fine-tuning during incremental phases and while significantly reducing the parameter overhead.
Authors: Lara Blomenkamp, Ivanna Kramer, Sabine Bauer, Theresa Sch\"oche
Abstract: In biomechanical modeling, the representation of ligament attachments is crucial for a realistic simulation of the forces acting between the vertebrae. These forces are typically modeled as vectors connecting ligament landmarks on adjacent vertebrae, making precise identification of these landmarks a key requirement for constructing reliable spine models. Existing automated detection methods are either limited to specific spinal regions or lack sufficient accuracy. This work presents a novel approach for detecting spinal ligament landmarks, which first performs shape-based segmentation of 3D vertebrae and subsequently applies domain-specific rules to identify different types of attachment points. The proposed method outperforms existing approaches by achieving high accuracy and demonstrating strong generalization across all spinal regions. Validation on two independent spinal datasets from multiple patients yielded a mean absolute error (MAE) of 0.7 mm and a root mean square error (RMSE) of 1.1 mm.
Authors: Xuewei Li, Xinghan Bao, Zhimin Chen, Xi Li
Abstract: As an important and challenging problem in computer vision, Panoramic Semantic Segmentation (PASS) aims to give complete scene perception based on an ultra-wide angle of view. Most PASS methods often focus on spherical geometry with RGB input or using the depth information in original or HHA format, which does not make full use of panoramic image geometry. To address these shortcomings, we propose REL-SF4PASS with our REL depth representation based on cylindrical coordinate and Spherical-dynamic Multi-Modal Fusion SMMF. REL is made up of Rectified Depth, Elevation-Gained Vertical Inclination Angle, and Lateral Orientation Angle, which fully represents 3D space in cylindrical coordinate style and the surface normal direction. SMMF aims to ensure the diversity of fusion for different panoramic image regions and reduce the breakage of cylinder side surface expansion in ERP projection, which uses different fusion strategies to match the different regions in panoramic images. Experimental results show that REL-SF4PASS considerably improves performance and robustness on popular benchmark, Stanford2D3D Panoramic datasets. It gains 2.35% average mIoU improvement on all 3 folds and reduces the performance variance by approximately 70% when facing 3D disturbance.
Authors: Chen-Ying Chien, Po-Chih Kuo
Abstract: Understanding how people perceive and evaluate interior spaces is essential for designing environments that promote well-being. However, predicting aesthetic experiences remains difficult due to the subjective nature of perception and the complexity of visual responses. This study introduces a dual-branch CNN-LSTM framework that fuses visual features with eye-tracking signals to predict aesthetic evaluations of residential interiors. We collected a dataset of 224 interior design videos paired with synchronized gaze data from 28 participants who rated 15 aesthetic dimensions. The proposed model attains 72.2% accuracy on objective dimensions (e.g., light) and 66.8% on subjective dimensions (e.g., relaxation), outperforming state-of-the-art video baselines and showing clear gains on subjective evaluation tasks. Notably, models trained with eye-tracking retain comparable performance when deployed with visual input alone. Ablation experiments further reveal that pupil responses contribute most to objective assessments, while the combination of gaze and visual cues enhances subjective evaluations. These findings highlight the value of incorporating eye-tracking as privileged information during training, enabling more practical tools for aesthetic assessment in interior design.
Authors: Chenxi Ruan, Yu Xiao, Yihan Hou, Guosheng Hu, Wei Zeng
Abstract: While text-to-image (T2I) models have advanced considerably, their capability to associate colors with implicit concepts remains underexplored. To address the gap, we introduce ColorConceptBench, a new human-annotated benchmark to systematically evaluate color-concept associations through the lens of probabilistic color distributions. ColorConceptBench moves beyond explicit color names or codes by probing how models translate 1,281 implicit color concepts using a foundation of 6,369 human annotations. Our evaluation of seven leading T2I models reveals that current models lack sensitivity to abstract semantics, and crucially, this limitation appears resistant to standard interventions (e.g., scaling and guidance). This demonstrates that achieving human-like color semantics requires more than larger models, but demands a fundamental shift in how models learn and represent implicit meaning.
Authors: Fangzheng Wu, Brian Summa
Abstract: We propose a validation-free checkpointing signal from a single forward-backward pass: the Frobenius norm of the classifier-head gradient on one detached-feature batch, ||g||_F = ||dL/dW||_F. Across ImageNet-1k CNNs and Transformers, this proxy is strongly negative with Top-1 and positive with loss. Selecting the checkpoint with the minimum head gradient in a short tail window closes most of the gap to the oracle (4.24% +/- 2.00% with a universal setup, about 1.12% with light per-family tuning). For practical deployment, a head-scale normalization is more stable within classic CNN families (e.g., ResNets), while a feature-scale normalization works well for Transformers and modern CNNs. The same one-batch probe also predicts COCO detection/segmentation mAP. In diffusion (UNet/DDPM on CIFAR-10), it tracks progress and enables near-oracle tail-window selection; it is positively correlated with same-distribution probe MSE and negatively with FID (lower is better), so it can be used as a lightweight, label-free monitor. Validation labels are never used beyond reporting. The probe adds much less than 0.1% of an epoch and works as a drop-in for validation-free checkpoint selection and early stopping.
Authors: Yangfan Xu, Lilian Zhang, Xiaofeng He, Pengdong Wu, Wenqi Wu, Jun Mao
Abstract: Transformer-based general visual geometry frameworks have shown promising performance in camera pose estimation and 3D scene understanding. Recent advancements in Visual Geometry Grounded Transformer (VGGT) models have shown great promise in camera pose estimation and 3D reconstruction. However, these models typically rely on ground truth labels for training, posing challenges when adapting to unlabeled and unseen scenes. In this paper, we propose a self-supervised framework to train VGGT with unlabeled data, thereby enhancing its localization capability in large-scale environments. To achieve this, we extend conventional pair-wise relations to sequence-wise geometric constraints for self-supervised learning. Specifically, in each sequence, we sample multiple source frames and geometrically project them onto different target frames, which improves temporal feature consistency. We formulate physical photometric consistency and geometric constraints as a joint optimization loss to circumvent the requirement for hard labels. By training the model with this proposed method, not only the local and global cross-view attention layers but also the camera and depth heads can effectively capture the underlying multi-view geometry. Experiments demonstrate that the model converges within hundreds of iterations and achieves significant improvements in large-scale localization. Our code will be released at https://github.com/X-yangfan/GPA-VGGT.
Authors: Nakul Poudel, Richard Simon, Cristian A. Linte
Abstract: Surgery is a highly complex process, and artificial intelligence has emerged as a transformative force in supporting surgical guidance and decision-making. However, the unimodal nature of most current AI systems limits their ability to achieve a holistic understanding of surgical workflows. This highlights the need for general-purpose surgical AI systems capable of comprehensively modeling the interrelated components of surgical scenes. Recent advances in large vision-language models that integrate multimodal data processing offer strong potential for modeling surgical tasks and providing human-like scene reasoning and understanding. Despite their promise, systematic investigations of VLMs in surgical applications remain limited. In this study, we evaluate the effectiveness of large VLMs for the fundamental surgical vision task of detecting surgical tools. Specifically, we investigate three state-of-the-art VLMs, Qwen2.5, LLaVA1.5, and InternVL3.5, on the GraSP robotic surgery dataset under both zero-shot and parameter-efficient LoRA fine-tuning settings. Our results demonstrate that Qwen2.5 consistently achieves superior detection performance in both configurations among the evaluated VLMs. Furthermore, compared with the open-set detection baseline Grounding DINO, Qwen2.5 exhibits stronger zero-shot generalization and comparable fine-tuned performance. Notably, Qwen2.5 shows superior instrument recognition, while Grounding DINO demonstrates stronger localization.
Authors: Justin Cui, Jie Wu, Ming Li, Tao Yang, Xiaojie Li, Rui Wang, Andrew Bai, Yuanhao Ban, Cho-Jui Hsieh
Abstract: Recent research in long-form video generation has shifted from bidirectional to autoregressive models, yet these methods commonly suffer from error accumulation and a loss of long-term coherence. While attention sink frames have been introduced to mitigate this performance decay, they often induce a critical failure mode we term sink-collapse: the generated content repeatedly reverts to the sink frame, resulting in abrupt scene resets and cyclic motion patterns. Our analysis reveals that sink-collapse originates from an inherent conflict between the periodic structure of Rotary Position Embedding (RoPE) and the multi-head attention mechanisms prevalent in current generative models. To address it, we propose a lightweight, training-free approach that effectively suppresses this behavior by introducing multi-head RoPE jitter that breaks inter-head attention homogenization and mitigates long-horizon collapse. Extensive experiments show that our method successfully alleviates sink-collapse while preserving generation quality. To the best of our knowledge, this work achieves the first demonstration of real-time, streaming, and infinite-length video generation with little quality decay. As an illustration of this robustness, we generate continuous videos up to 12 hours in length, which, to our knowledge, is among the longest publicly demonstrated results in streaming video generation.
Authors: Jingran Zhang, Ning Li, Yuanhao Ban, Andrew Bai, Justin Cui
Abstract: While most prior work in video generation relies on bidirectional architectures, recent efforts have sought to adapt these models into autoregressive variants to support near real-time generation. However, such adaptations often depend heavily on teacher models, which can limit performance, particularly in the absence of a strong autoregressive teacher, resulting in output quality that typically lags behind their bidirectional counterparts. In this paper, we explore an alternative approach that uses reward signals to guide the generation process, enabling more efficient and scalable autoregressive generation. By using reward signals to guide the model, our method simplifies training while preserving high visual fidelity and temporal consistency. Through extensive experiments on standard benchmarks, we find that our approach performs comparably to existing autoregressive models and, in some cases, surpasses similarly sized bidirectional models by avoiding constraints imposed by teacher architectures. For example, on VBench, our method achieves a total score of 84.92, closely matching state-of-the-art autoregressive methods that score 84.31 but require significant heterogeneous distillation.
Authors: Ba-Thinh Lam, Thanh-Huy Nguyen, Hoang-Thien Nguyen, Quang-Khai Bui-Tran, Nguyen Lan Vi Vu, Phat K. Huynh, Ulas Bagci, Min Xu
Abstract: Deep learning has shown remarkable progress in medical image semantic segmentation, yet its success heavily depends on large-scale expert annotations and consistent data distributions. In practice, annotations are scarce, and images are collected from multiple scanners or centers, leading to mixed-domain settings with unknown domain labels and severe domain gaps. Existing semi-supervised or domain adaptation approaches typically assume either a single domain shift or access to explicit domain indices, which rarely hold in real-world deployment. In this paper, we propose a domain-invariant mixed-domain semi-supervised segmentation framework that jointly enhances data diversity and mitigates domain bias. A Copy-Paste Mechanism (CPM) augments the training set by transferring informative regions across domains, while a Cluster Maximum Mean Discrepancy (CMMD) block clusters unlabeled features and aligns them with labeled anchors via an MMD objective, encouraging domain-invariant representations. Integrated within a teacher-student framework, our method achieves robust and precise segmentation even with very few labeled examples and multiple unknown domain discrepancies. Experiments on Fundus and M&Ms benchmarks demonstrate that our approach consistently surpasses semi-supervised and domain adaptation methods, establishing a potential solution for mixed-domain semi-supervised medical image segmentation.
Authors: Zirui Wang, Junyi Zhang, Jiaxin Ge, Long Lian, Letian Fu, Lisa Dunlap, Ken Goldberg, XuDong Wang, Ion Stoica, David M. Chan, Sewon Min, Joseph E. Gonzalez
Abstract: Modern Vision-Language Models (VLMs) remain poorly characterized in multi-step visual interactions, particularly in how they integrate perception, memory, and action over long horizons. We introduce VisGym, a gymnasium of 17 environments for evaluating and training VLMs. The suite spans symbolic puzzles, real-image understanding, navigation, and manipulation, and provides flexible controls over difficulty, input representation, planning horizon, and feedback. We also provide multi-step solvers that generate structured demonstrations, enabling supervised finetuning. Our evaluations show that all frontier models struggle in interactive settings, achieving low success rates in both the easy (46.6%) and hard (26.0%) configurations. Our experiments reveal notable limitations: models struggle to effectively leverage long context, performing worse with an unbounded history than with truncated windows. Furthermore, we find that several text-based symbolic tasks become substantially harder once rendered visually. However, explicit goal observations, textual feedback, and exploratory demonstrations in partially observable or unknown-dynamics settings for supervised finetuning yield consistent gains, highlighting concrete failure modes and pathways for improving multi-step visual decision-making. Code, data, and models can be found at: https://visgym.github.io/.
Authors: David Serrano-Lozano, Anand Bhattad, Luis Herranz, Jean-Fran\c{c}ois Lalonde, Javier Vazquez-Corral
Abstract: We present SyncLight, the first method to enable consistent, parametric relighting across multiple uncalibrated views of a static scene. While single-view relighting has advanced significantly, existing generative approaches struggle to maintain the rigorous lighting consistency essential for multi-camera broadcasts, stereoscopic cinema, and virtual production. SyncLight addresses this by enabling precise control over light intensity and color across a multi-view capture of a scene, conditioned on a single reference edit. Our method leverages a multi-view diffusion transformer trained using a latent bridge matching formulation, achieving high-fidelity relighting of the entire image set in a single inference step. To facilitate training, we introduce a large-scale hybrid dataset comprising diverse synthetic environments -- curated from existing sources and newly designed scenes -- alongside high-fidelity, real-world multi-view captures under calibrated illumination. Surprisingly, though trained only on image pairs, SyncLight generalizes zero-shot to an arbitrary number of viewpoints, effectively propagating lighting changes across all views, without requiring camera pose information. SyncLight enables practical relighting workflows for multi-view capture systems.
Authors: Basile Van Hoorick, Dian Chen, Shun Iwase, Pavel Tokmakov, Muhammad Zubair Irshad, Igor Vasiljevic, Swati Gupta, Fangzhou Cheng, Sergey Zakharov, Vitor Campagnolo Guizilini
Abstract: Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consistency in highly dynamic real-world environments. In this work, we introduce \textbf{AnyView}, a diffusion-based video generation framework for \emph{dynamic view synthesis} with minimal inductive biases or geometric assumptions. We leverage multiple data sources with various levels of supervision, including monocular (2D), multi-view static (3D) and multi-view dynamic (4D) datasets, to train a generalist spatiotemporal implicit representation capable of producing zero-shot novel videos from arbitrary camera locations and trajectories. We evaluate AnyView on standard benchmarks, showing competitive results with the current state of the art, and propose \textbf{AnyViewBench}, a challenging new benchmark tailored towards \emph{extreme} dynamic view synthesis in diverse real-world scenarios. In this more dramatic setting, we find that most baselines drastically degrade in performance, as they require significant overlap between viewpoints, while AnyView maintains the ability to produce realistic, plausible, and spatiotemporally consistent videos when prompted from \emph{any} viewpoint. Results, data, code, and models can be viewed at: https://tri-ml.github.io/AnyView/
Authors: Ayan Banerjee, Komandoor Srivathsan, Sandeep K. S. Gupta
Abstract: A desirable property of any deployed artificial intelligence is generalization across domains, i.e. data generation distribution under a specific acquisition condition. In medical imagining applications the most coveted property for effective deployment is Single Domain Generalization (SDG), which addresses the challenge of training a model on a single domain to ensure it generalizes well to unseen target domains. In multi-center studies, differences in scanners and imaging protocols introduce domain shifts that exacerbate variability in rare class characteristics. This paper presents our experience on SDG in real life deployment for two exemplary medical imaging case studies on seizure onset zone detection using fMRI data, and stress electrocardiogram based coronary artery detection. Utilizing the commonly used application of diabetic retinopathy, we first demonstrate that state-of-the-art SDG techniques fail to achieve generalized performance across data domains. We then develop a generic expert knowledge integrated deep learning technique DL+EKE and instantiate it for the DR application and show that DL+EKE outperforms SOTA SDG methods on DR. We then deploy instances of DL+EKE technique on the two real world examples of stress ECG and resting state (rs)-fMRI and discuss issues faced with SDG techniques.
Authors: Soumitri Chattopadhyay, Basar Demir, Marc Niethammer
Abstract: While 3D foundational models have shown promise for promptable segmentation of medical volumes, their robustness to imprecise prompts remains under-explored. In this work, we aim to address this gap by systematically studying the effect of various controlled perturbations of dense visual prompts, that closely mimic real-world imprecision. By conducting experiments with two recent foundational models on a multi-organ abdominal segmentation task, we reveal several facets of promptable medical segmentation, especially pertaining to reliance on visual shape and spatial cues, and the extent of resilience of models towards certain perturbations. Codes are available at: https://github.com/ucsdbiag/Prompt-Robustness-MedSegFMs
URLs: https://github.com/ucsdbiag/Prompt-Robustness-MedSegFMs
Authors: Qinglong Cao, Yuntian Chen, Chao Ma, Xiaokang Yang
Abstract: Multimodal large language models (MLLMs) have shown remarkable capabilities in multimodal perception and understanding tasks. However, their effectiveness in specialized domains, such as remote sensing and medical imaging, remains limited. A natural approach to domain adaptation is to inject domain knowledge through textual instructions, prompts, or auxiliary captions. Surprisingly, we find that such input-level domain knowledge injection yields little to no improvement on scientific multimodal tasks, even when the domain knowledge is explicitly provided. This observation suggests that current MLLMs fail to internalize domain-specific priors through language alone, and that domain knowledge must be integrated at the optimization level. Motivated by this insight, we propose a reinforcement fine-tuning framework that incorporates domain knowledge directly into the learning objective. Instead of treating domain knowledge as descriptive information, we encode it as domain-informed constraints and reward signals, shaping the model's behavior in the output space. Extensive experiments across multiple datasets in remote sensing and medical domains consistently demonstrate good performance gains, achieving state-of-the-art results on multimodal domain tasks. Our results highlight the necessity of optimization-level domain knowledge integration and reveal a fundamental limitation of textual domain conditioning in current MLLMs.
Authors: Wei Song, Zhenchang Xing, Liming Zhu, Yulei Sui, Jingling Xue
Abstract: The rapid proliferation of realistic deepfakes has raised urgent concerns over their misuse, motivating the use of defensive watermarks in synthetic images for reliable detection and provenance tracking. However, this defense paradigm assumes such watermarks are inherently resistant to removal. We challenge this assumption with DeMark, a query-free black-box attack framework that targets defensive image watermarking schemes for deepfakes. DeMark exploits latent-space vulnerabilities in encoder-decoder watermarking models through a compressive sensing based sparsification process, suppressing watermark signals while preserving perceptual and structural realism appropriate for deepfakes. Across eight state-of-the-art watermarking schemes, DeMark reduces watermark detection accuracy from 100% to 32.9% on average while maintaining natural visual quality, outperforming existing attacks. We further evaluate three defense strategies, including image super resolution, sparse watermarking, and adversarial training, and find them largely ineffective. These results demonstrate that current encoder decoder watermarking schemes remain vulnerable to latent-space manipulations, underscoring the need for more robust watermarking methods to safeguard against deepfakes.
Authors: Xianya Fang, Feiyang Ren, Xiang Chen, Yu Tian, Zhen Bi, Haiyang Yu, Sheng-Jun Huang
Abstract: Multimodal LLMs are powerful but prone to object hallucinations, which describe non-existent entities and harm reliability. While recent unlearning methods attempt to mitigate this, we identify a critical flaw: structural fragility. We empirically demonstrate that standard erasure achieves only superficial suppression, trapping the model in sharp minima where hallucinations catastrophically resurge after lightweight relearning. To ensure geometric stability, we propose SARE, which casts unlearning as a targeted min-max optimization problem and uses a Targeted-SAM mechanism to explicitly flatten the loss landscape around hallucinated concepts. By suppressing hallucinations under simulated worst-case parameter perturbations, our framework ensures robust removal stable against weight shifts. Extensive experiments demonstrate that SARE significantly outperforms baselines in erasure efficacy while preserving general generation quality. Crucially, it maintains persistent hallucination suppression against relearning and parameter updates, validating the effectiveness of geometric stabilization.
Authors: Xiaobin Li, Run Zhang
Abstract: Nonlinear dimensionality reduction techniques, particularly UMAP, are widely used for visualizing high-dimensional data. However, UMAP's local Euclidean distance assumption often fails to capture intrinsic manifold geometry, leading to topological tearing and structural collapse. We identify UMAP's sensitivity to the k-nearest neighbor graph as a key cause. To address this, we introduce Ollivier-Ricci curvature as a geometric prior, reinforcing edges at geometric bottlenecks and reducing redundant links. Since curvature estimation is noise-sensitive, we also incorporate a topological prior using Jaccard similarity to ensure neighborhood consistency. The resulting method, JORC-UMAP, better distinguishes true manifold structure from spurious connections. Experiments on synthetic and real-world datasets show that JORC-UMAP reduces tearing and collapse more effectively than standard UMAP and other DR methods, as measured by SVM accuracy and triplet preservation scores, while maintaining computational efficiency. This work offers a geometry-aware enhancement to UMAP for more faithful data visualization.
Authors: Ming Kang, Fung Fung Ting, Rapha\"el C. -W. Phan, Zongyuan Ge, Chee-Ming Ting
Abstract: Nuclei panoptic segmentation supports cancer diagnostics by integrating both semantic and instance segmentation of different cell types to analyze overall tissue structure and individual nuclei in histopathology images. Major challenges include detecting small objects, handling ambiguous boundaries, and addressing class imbalance. To address these issues, we propose PanopMamba, a novel hybrid encoder-decoder architecture that integrates Mamba and Transformer with additional feature-enhanced fusion via state space modeling. We design a multiscale Mamba backbone and a State Space Model (SSM)-based fusion network to enable efficient long-range perception in pyramid features, thereby extending the pure encoder-decoder framework while facilitating information sharing across multiscale features of nuclei. The proposed SSM-based feature-enhanced fusion integrates pyramid feature networks and dynamic feature enhancement across different spatial scales, enhancing the feature representation of densely overlapping nuclei in both semantic and spatial dimensions. To the best of our knowledge, this is the first Mamba-based approach for panoptic segmentation. Additionally, we introduce alternative evaluation metrics, including image-level Panoptic Quality ($i$PQ), boundary-weighted PQ ($w$PQ), and frequency-weighted PQ ($fw$PQ), which are specifically designed to address the unique challenges of nuclei segmentation and thereby mitigate the potential bias inherent in vanilla PQ. Experimental evaluations on two multiclass nuclei segmentation benchmark datasets, MoNuSAC2020 and NuInsSeg, demonstrate the superiority of PanopMamba for nuclei panoptic segmentation over state-of-the-art methods. Consequently, the robustness of PanopMamba is validated across various metrics, while the distinctiveness of PQ variants is also demonstrated. Code is available at https://github.com/mkang315/PanopMamba.
Authors: Maxence Noble, Gonzalo I\~naki Quintana, Benjamin Aubin, Cl\'ement Chadebec
Abstract: Diffusion-based image super-resolution (SR) has recently attracted significant attention by leveraging the expressive power of large pre-trained text-to-image diffusion models (DMs). A central practical challenge is resolving the trade-off between reconstruction faithfulness and photorealism. To address inference efficiency, many recent works have explored knowledge distillation strategies specifically tailored to SR, enabling one-step diffusion-based approaches. However, these teacher-student formulations are inherently constrained by information compression, which can degrade perceptual cues such as lifelike textures and depth of field, even with high overall perceptual quality. In parallel, self-distillation DMs, known as Flow Map models, have emerged as a promising alternative for image generation tasks, enabling fast inference while preserving the expressivity and training stability of standard DMs. Building on these developments, we propose FlowMapSR, a novel diffusion-based framework for image super-resolution explicitly designed for efficient inference. Beyond adapting Flow Map models to SR, we introduce two complementary enhancements: (i) positive-negative prompting guidance, based on a generalization of classifier free-guidance paradigm to Flow Map models, and (ii) adversarial fine-tuning using Low-Rank Adaptation (LoRA). Among the considered Flow Map formulations (Eulerian, Lagrangian, and Shortcut), we find that the Shortcut variant consistently achieves the best performance when combined with these enhancements. Extensive experiments show that FlowMapSR achieves a better balance between reconstruction faithfulness and photorealism than recent state-of-the-art methods for both x4 and x8 upscaling, while maintaining competitive inference time. Notably, a single model is used for both upscaling factors, without any scale-specific conditioning or degradation-guided mechanisms.
Authors: Zhuohao Li, Yinghao Li, Jian-Jian Jiang, Lang Zhou, Tianyu Zhang, Wei-Shi Zheng
Abstract: Vision-Language-Action (VLA) models have advanced robotic manipulation by combining vision, language, and proprioception to predict actions. However, previous methods fuse proprioceptive signals directly with VLM-encoded vision-language features, resulting in state-dominant bias and false completions despite visible execution failures. We attribute this to modality imbalance, where policies over-rely on internal state while underusing visual evidence. To address this, we present ReViP, a novel VLA framework with Vision-Proprioception Rebalance to enhance visual grounding and robustness under perturbations. The key insight is to introduce auxiliary task-aware environment priors to adaptively modulate the coupling between semantic perception and proprioceptive dynamics. Specifically, we use an external VLM as a task-stage observer to extract real-time task-centric visual cues from visual observations, which drive a Vision-Proprioception Feature-wise Linear Modulation to enhance environmental awareness and reduce state-driven errors. Moreover, to evaluate false completion, we propose the first False-Completion Benchmark Suite built on LIBERO with controlled settings such as Object-Drop. Extensive experiments show that ReViP effectively reduces false-completion rates and improves success rates over strong VLA baselines on our suite, with gains extending to LIBERO, RoboTwin 2.0, and real-world evaluations.
Authors: Xinze Li, Ziyue Zhu, Siyuan Liu, Yubo Ma, Yuhang Zang, Yixin Cao, Aixin Sun
Abstract: We introduce EMemBench, a programmatic benchmark for evaluating long-term memory of agents through interactive games. Rather than using a fixed set of questions, EMemBench generates questions from each agent's own trajectory, covering both text and visual game environments. Each template computes verifiable ground truth from underlying game signals, with controlled answerability and balanced coverage over memory skills: single/multi-hop recall, induction, temporal, spatial, logical, and adversarial. We evaluate memory agents with strong LMs/VLMs as backbones, using in-context prompting as baselines. Across 15 text games and multiple visual seeds, results are far from saturated: induction and spatial reasoning are persistent bottlenecks, especially in visual setting. Persistent memory yields clear gains for open backbones on text games, but improvements are less consistent for VLM agents, suggesting that visually grounded episodic memory remains an open challenge. A human study further confirms the difficulty of EMemBench.
Authors: Crispian Morris, Imogen Dexter, Fan Zhang, David R. Bull, Nantheera Anantrasirichai
Abstract: Live video denoising under realistic, multi-component sensor noise remains challenging for applications such as autofocus, autonomous driving, and surveillance. We propose PocketDVDNet, a lightweight video denoiser developed using our model compression framework that combines sparsity-guided structured pruning, a physics-informed noise model, and knowledge distillation to achieve high-quality restoration with reduced resource demands. Starting from a reference model, we induce sparsity, apply targeted channel pruning, and retrain a teacher on realistic multi-component noise. The student network learns implicit noise handling, eliminating the need for explicit noise-map inputs. PocketDVDNet reduces the original model size by 74% while improving denoising quality and processing 5-frame patches in real-time. These results demonstrate that aggressive compression, combined with domain-adapted distillation, can reconcile performance and efficiency for practical, real-time video denoising.
Authors: Robin Young, Srinivasan Keshav
Abstract: Reliable wall-to-wall biomass mapping from NASA's GEDI mission requires interpolating sparse LiDAR observations across heterogeneous landscapes. While machine learning approaches like Random Forest and XGBoost are standard for this task, they treat spatial predictions of GEDI observations from multispectral or SAR remote sensing data as independent without adapting to the varying difficulty of heterogeneous landscapes. We demonstrate these approaches generally fail to produce calibrated prediction intervals. We identify that this stems from conflating ensemble variance with aleatoric uncertainty and ignoring local spatial context. To resolve this, we introduce Attentive Neural Processes (ANPs), a probabilistic meta-learning framework that explicitly conditions predictions on local observation sets and geospatial foundation model embeddings. Unlike static ensembles, ANPs learn a flexible spatial covariance function, allowing uncertainty estimates to expand in complex landscapes and contract in homogeneous areas. We validate this approach across five distinct biomes ranging from Tropical Amazonian forests to Boreal and Alpine ecosystems, demonstrating that ANPs achieve competitive accuracy while maintaining near-ideal uncertainty calibration. We demonstrate the operational utility of the method through few-shot adaptation, where the model recovers most of the performance gap in cross-region transfer using minimal local data. This work provides a scalable, theoretically rigorous alternative to ensemble variance for continental scale earth observation.
Authors: Madeline C. Lisaius, Srinivasan Keshav, Andrew Blake, Clement Atzberger
Abstract: Crop type maps from satellite remote sensing are important tools for food security, local livelihood support and climate change mitigation in smallholder regions of the world, but most satellite-based methods are not well suited to smallholder conditions. To address this gap, we establish a four-part criteria for a useful embedding-based approach consisting of 1) performance, 2) plausibility, 3) transferability and 4) accessibility and evaluate geospatial foundation model (FM) embeddings -based approaches using TESSERA and AlphaEarth against current baseline methods for a region in the groundnut basin of Senegal. We find that the TESSERA -based approach to land cover and crop type mapping fulfills the selection criteria best, and in one temporal transfer example shows 28% higher accuracy compared to the next best method. These results indicate that TESSERA embeddings are an effective approach for crop type classification and mapping tasks in Senegal.
Authors: Kun Huang, Fanglue Zhang, Neil Dodgson
Abstract: The presence of spherical distortion in equirectangular projection (ERP) images presents a persistent challenge in dense regression tasks such as surface normal estimation. Although it may appear straightforward to repurpose architectures developed for 360{\deg} depth estimation, our empirical findings indicate that such models yield suboptimal performance when applied to surface normal prediction. This is largely attributed to their architectural bias toward capturing global scene layout, which comes at the expense of the fine-grained local geometric cues that are critical for accurate surface orientation estimation. While convolutional neural networks (CNNs) have been employed to mitigate spherical distortion, their fixed receptive fields limit their ability to capture holistic scene structure. Conversely, vision transformers (ViTs) are capable of modeling long-range dependencies via global self-attention, but often fail to preserve high-frequency local detail. To address these limitations, we propose \textit{PanoNormal}, a monocular surface normal estimation architecture for 360{\deg} images that integrates the complementary strengths of CNNs and ViTs. In particular, we design a multi-level global self-attention mechanism that explicitly accounts for the spherical feature distribution, enabling our model to recover both global contextual structure and local geometric details. Experimental results demonstrate that our method not only achieves state-of-the-art performance on several benchmark 360{\deg} datasets, but also significantly outperforms adapted depth estimation models on the task of surface normal prediction. The code and model are available at https://github.com/huangkun101230/PanoNormal.
Authors: Andrea Dunn Beltran, Daniel Rho, Marc Niethammer, Roni Sengupta
Abstract: Simultaneous Localization and Mapping (SLAM) systems typically assume static, distant illumination; however, many real-world scenarios, such as endoscopy, subterranean robotics, and search & rescue in collapsed environments, require agents to operate with a co-located light and camera in the absence of external lighting. In such cases, dynamic near-field lighting introduces strong, view-dependent shading that significantly degrades SLAM performance. We introduce Near-Field Lighting Bundle Adjustment Loss (NFL-BA) which explicitly models near-field lighting as a part of Bundle Adjustment loss and enables better performance for scenes captured with dynamic lighting. NFL-BA can be integrated into neural rendering-based SLAM systems with implicit or explicit scene representations. Our evaluations mainly focus on endoscopy procedure where SLAM can enable autonomous navigation, guidance to unsurveyed regions, blindspot detections, and 3D visualizations, which can significantly improve patient outcomes and endoscopy experience for both physicians and patients. Replacing Photometric Bundle Adjustment loss of SLAM systems with NFL-BA leads to significant improvement in camera tracking, 37% for MonoGS and 14% for EndoGS, and leads to state-of-the-art camera tracking and mapping performance on the C3VD colonoscopy dataset. Further evaluation on indoor scenes captured with phone camera with flashlight turned on, also demonstrate significant improvement in SLAM performance due to NFL-BA. See results at https://asdunnbe.github.io/NFL-BA/
Authors: Xuyang Guo, Jiayan Huo, Yingyu Liang, Zhenmei Shi, Zhao Song, Jiahao Zhang, Zhen Zhuang
Abstract: Generative modeling is widely regarded as one of the most essential problems in today's AI community, with text-to-image generation having gained unprecedented real-world impacts. Among various approaches, diffusion models have achieved remarkable success and have become the de facto solution for text-to-image generation. However, despite their impressive performance, these models exhibit fundamental limitations in adhering to numerical constraints in user instructions, frequently generating images with an incorrect number of objects. While several prior works have mentioned this issue, a comprehensive and rigorous evaluation of this limitation remains lacking. To address this gap, we introduce T2ICountBench, a novel benchmark designed to rigorously evaluate the counting ability of state-of-the-art text-to-image diffusion models. Our benchmark encompasses a diverse set of generative models, including both open-source and private systems. It explicitly isolates counting performance from other capabilities, provides structured difficulty levels, and incorporates human evaluations to ensure high reliability. Extensive evaluations with T2ICountBench reveal that all state-of-the-art diffusion models fail to generate the correct number of objects, with accuracy dropping significantly as the number of objects increases. Additionally, an exploratory study on prompt refinement demonstrates that such simple interventions generally do not improve counting accuracy. Our findings highlight the inherent challenges in numerical understanding within diffusion models and point to promising directions for future improvements.
Authors: Hung Q. Vo, Pengyu Yuan, Zheng Yin, Kelvin K. Wong, Chika F. Ezeana, Son T. Ly, Hien V. Nguyen, Stephen T. C. Wong
Abstract: Self-supervised learning (SSL) with Vision Transformers (ViT) has shown immense potential in medical image analysis. However, the quadratic complexity ($\mathcal{O}(N^2)$) of standard self-attention poses a severe barrier for high-resolution biomedical tasks, effectively excluding resource-constrained research labs from utilizing state-of-the-art models. To address this computational bottleneck without sacrificing diagnostic accuracy, we propose \textbf{MIRAM}, a Multi-scale Masked Autoencoder that leverages a \textbf{hybrid-attention mechanism}. Our architecture uniquely decouples semantic learning from detail reconstruction using a dual-decoder design: a standard transformer decoder captures global semantics at low resolution, while a linear-complexity decoder (comparing Linformer, Performer, and Nystr\"omformer) handles the computationally expensive high-resolution reconstruction. This reduces the complexity of the upscaling stage from quadratic to linear ($\mathcal{O}(N)$), enabling high-fidelity training on consumer-grade GPUs. We validate our approach on the CBIS-DDSM mammography dataset. Remarkably, our \textbf{Nystr\"omformer-based variant} achieves a classification accuracy of \textbf{61.0\%}, outperforming both standard MAE (58.9\%) and MoCo-v3 (60.2\%) while requiring significantly less memory. These results demonstrate that hybrid-attention architectures can democratize high-resolution medical AI, making powerful SSL accessible to researchers with limited hardware resources.
Authors: Yang Li, Soumya Snigdha Kundu, Maxence Boels, Toktam Mahmoodi, Sebastien Ourselin, Tom Vercauteren, Prokar Dasgupta, Jonathan Shapey, Alejandro Granados
Abstract: Surgical object detection in laparoscopic videos enables real-time instrument identification for workflow analysis and skills assessment, but training robust models such as You Only Look Once (YOLO) is challenged by limited data, privacy constraints, and inter-institutional variability. Federated learning (FL) enables collaborative training without sharing raw data, yet practical support for modern YOLO pipelines under heterogeneous surgical data remains limited. We present UltraFlwr, an open-source, communication-efficient, and edge-deployable framework that integrates Ultralytics YOLO with the Flower FL platform and supports native Partial Aggregation (PA) of YOLO components (backbone, neck, head). Using two public laparoscopic surgical tool detection datasets, we conduct a systematic empirical study of federated YOLO training under Independent and Identically Distributed (IID) and multiple clinically motivated heterogeneous scenarios, including differences in data curation, video length, and label availability. Results show that standard FL aggregators (e.g., FedAvg) do not consistently match centralized training per client, but reduce inter-client performance variability. Aggregating both backbone and neck components achieves performance comparable to full aggregation with lower communication costs. Also, improving within-client data consistency can benefit FL even when it increases distribution shift across clients. These findings provide practical guidance for deploying federated YOLO-based object detection in heterogeneous surgical environments. UltraFlwr is publicly available at https://github.com/KCL-BMEIS/UltraFlwr.
Authors: Yinzhe Wu, Hongyu Rui, Fanwen Wang, Jiahao Huang, Zhenxuan Zhang, Haosen Zhang, Zi Wang, Guang Yang
Abstract: Multi-contrast super-resolution (MCSR) is crucial for enhancing MRI but current deep learning methods are limited. They typically require large, paired low- and high-resolution (LR/HR) training datasets, which are scarce, and are trained for fixed upsampling scales. While recent self-supervised methods remove the paired data requirement, they fail to leverage valuable population-level priors. In this work, we propose a novel, decoupled MCSR framework that resolves both limitations. We reformulate MCSR into two stages: (1) an unpaired cross-modal synthesis (uCMS) module, trained once on unpaired population data to learn a robust anatomical prior; and (2) a lightweight, patient-specific implicit re-representation (IrR) module. This IrR module is optimized in a self-supervised manner to fuse the population prior with the subject's own LR target data. This design uniquely fuses population-level knowledge with patient-specific fidelity without requiring any paired LR/HR or paired cross-modal training data. By building the IrR module on an implicit neural representation, our framework is also inherently scale-agnostic. Our method demonstrates superior quantitative performance on different datasets, with exceptional robustness at extreme scales (16x, 32x), a regime where competing methods fail. Our work presents a data-efficient, flexible, and computationally lightweight paradigm for MCSR, enabling high-fidelity, arbitrary-scale
Authors: Rui-Yang Ju, Sheng-Yen Huang, Yi-Ping Hung
Abstract: The introduction of 3D Gaussian blendshapes has enabled the real-time reconstruction of animatable head avatars from monocular video. Toonify, a StyleGAN-based method, has become widely used for facial image stylization. To extend Toonify for synthesizing diverse stylized 3D head avatars using Gaussian blendshapes, we propose an efficient two-stage framework, ToonifyGB. In Stage 1 (stylized video generation), we adopt an improved StyleGAN to generate the stylized video from the input video frames, which overcomes the limitation of cropping aligned faces at a fixed resolution as preprocessing for normal StyleGAN. This process provides a more stable stylized video, which enables Gaussian blendshapes to better capture the high-frequency details of the video frames, facilitating the synthesis of high-quality animations in the next stage. In Stage 2 (Gaussian blendshapes synthesis), our method learns a stylized neutral head model and a set of expression blendshapes from the generated stylized video. By combining the neutral head model with expression blendshapes, ToonifyGB can efficiently render stylized avatars with arbitrary expressions. We validate the effectiveness of ToonifyGB on benchmark datasets using two representative styles: Arcane and Pixar.
Authors: Divyanshu Mishra, Mohammadreza Salehi, Pramit Saha, Olga Patey, Aris T. Papageorghiou, Yuki M. Asano, J. Alison Noble
Abstract: Self-supervised learning (SSL) has achieved major advances in natural images and video understanding, but challenges remain in domains like echocardiography (heart ultrasound) due to subtle anatomical structures, complex temporal dynamics, and the current lack of domain-specific pre-trained models. Existing SSL approaches such as contrastive, masked modeling, and clustering-based methods struggle with high intersample similarity, sensitivity to low PSNR inputs common in ultrasound, or aggressive augmentations that distort clinically relevant features. We present DISCOVR (Distilled Image Supervision for Cross Modal Video Representation), a self-supervised dual branch framework for cardiac ultrasound video representation learning. DISCOVR combines a clustering-based video encoder that models temporal dynamics with an online image encoder that extracts fine-grained spatial semantics. These branches are connected through a semantic cluster distillation loss that transfers anatomical knowledge from the evolving image encoder to the video encoder, enabling temporally coherent representations enriched with fine-grained semantic understanding.Evaluated on six echocardiography datasets spanning fetal, pediatric, and adult populations, DISCOVR outperforms both specialized video anomaly detection methods and state-of-the-art video-SSL baselines in zero-shot and linear probing setups,achieving superior segmentation transfer and strong downstream performance on clinically relevant tasks such as LVEF prediction. Code available at: https://github.com/mdivyanshu97/DISCOVR
Authors: Chi-Yao Huang, Zeel Bhatt, Yezhou Yang
Abstract: Breakthroughs in visual odometry (VO) have fundamentally reshaped the landscape of robotics, enabling ultra-precise camera state estimation that is crucial for modern autonomous systems. Despite these advances, many learning-based VO techniques rely on rigid geometric assumptions, which often fall short in interpretability and lack a solid theoretical basis within fully data-driven frameworks. To overcome these limitations, we introduce VOCAL (Visual Odometry via ContrAstive Learning), a novel framework that reimagines VO as a label ranking challenge. By integrating Bayesian inference with a representation learning framework, VOCAL organizes visual features to mirror camera states. The ranking mechanism compels similar camera states to converge into consistent and spatially coherent representations within the latent space. This strategic alignment not only bolsters the interpretability of the learned features but also ensures compatibility with multimodal data sources. Extensive evaluations on the KITTI dataset highlight VOCAL's enhanced interpretability and flexibility, pushing VO toward more general and explainable spatial intelligence.
Authors: Vera Soboleva, Aibek Alanov, Andrey Kuznetsov, Konstantin Sobolev
Abstract: While diffusion model fine-tuning offers a powerful approach for customizing pre-trained models to generate specific objects, it frequently suffers from overfitting when training samples are limited, compromising both generalization capability and output diversity. This paper tackles the challenging yet most impactful task of adapting a diffusion model using just a single concept image, as single-image customization holds the greatest practical potential. We introduce T-LoRA, a Timestep-Dependent Low-Rank Adaptation framework specifically designed for diffusion model personalization. We show that higher diffusion timesteps are more prone to overfitting than lower ones, necessitating a timestep-sensitive fine-tuning strategy. T-LoRA incorporates two key innovations: (1) a dynamic fine-tuning strategy that adjusts rank-constrained updates based on diffusion timesteps, and (2) a weight parametrization technique that ensures independence between adapter components through orthogonal initialization. Extensive experiments on SD-XL and FLUX-1.dev show that T-LoRA and its individual components outperform standard LoRA and other diffusion model personalization techniques, achieving a superior balance between concept fidelity and text alignment. Project page is available at https://controlgenai.github.io/T-LoRA/.
Authors: Mengxi Liu, Lala Shakti Swarup Ray, Sizhen Bian, Ko Watanabe, Ankur Bhatt, Joanna Sorysz, Russel Torah, Bo Zhou, Paul Lukowicz
Abstract: We present NeckSense, a novel wearable system for head pose tracking that leverages multi-channel bio-impedance sensing with soft, dry electrodes embedded in a lightweight, necklace-style form factor. NeckSense captures dynamic changes in tissue impedance around the neck, which are modulated by head rotations and subtle muscle activations. To robustly estimate head pose, we propose a deep learning framework that integrates anatomical priors, including joint constraints and natural head rotation ranges, into the loss function design. We validate NeckSense on 7 participants using the current SOTA pose estimation model as ground truth. Our system achieves a mean per-vertex error of 25.9 mm across various head movements with a leave-one-person-out cross-validation method, demonstrating that a compact, line-of-sight-free bio-impedance wearable can deliver head-tracking performance comparable to SOTA vision-based methods.
Authors: Hongyu Guo, Xiangzhao Hao, Jiarui Guo, Haiyun Guo, Jinqiao Wang, Tat-Seng Chua
Abstract: Few-shot fine-grained visual classification (FGVC) aims to leverage limited data to enable models to discriminate subtly distinct categories. Recent works mostly finetuned the pre-trained visual language models to achieve performance gain, yet suffering from overfitting and weak generalization. To deal with this, we introduce UniFGVC, a universal training-free framework that reformulates few-shot FGVC as multimodal retrieval. First, we propose the Category-Discriminative Visual Captioner (CDV-Captioner) to exploit the open-world knowledge of multimodal large language models (MLLMs) to generate a structured text description that captures the fine-grained attribute features distinguishing closely related classes. CDV-Captioner uses chain-of-thought prompting and visually similar reference images to reduce hallucination and enhance discrimination of generated captions. Using it we can convert each image into an image-description pair, enabling more comprehensive feature representation, and construct the multimodal category templates using few-shot samples for the subsequent retrieval pipeline. Then, off-the-shelf vision and text encoders embed query and template pairs, and FGVC is accomplished by retrieving the nearest template in the joint space. UniFGVC ensures broad compatibility with diverse MLLMs and encoders, offering reliable generalization and adaptability across few-shot FGVC scenarios. Extensive experiments on 12 FGVC benchmarks demonstrate its consistent superiority over prior few-shot CLIP-based methods and even several fully-supervised MLLMs-based approaches.
Authors: Zhe Zhu, Honghua Chen, Peng Li, Mingqiang Wei
Abstract: Text-driven 3D editing seeks to modify 3D scenes according to textual descriptions, and most existing approaches tackle this by adapting pre-trained 2D image editors to multi-view inputs. However, without explicit control over multi-view information exchange, they often fail to maintain cross-view consistency, leading to insufficient edits and blurry details. We introduce CoreEditor, a novel framework for consistent text-to-3D editing. The key innovation is a correspondence-constrained attention mechanism that enforces precise interactions between pixels expected to remain consistent throughout the diffusion denoising process. Beyond relying solely on geometric alignment, we further incorporate semantic similarity estimated during denoising, enabling more reliable correspondence modeling and robust multi-view editing. In addition, we design a selective editing pipeline that allows users to choose preferred results from multiple candidates, offering greater flexibility and user control. Extensive experiments show that CoreEditor produces high-quality, 3D-consistent edits with sharper details, significantly outperforming prior methods.
Authors: Wasi Ullah, Yasir Noman Khalid, Saddam Hussain Khan
Abstract: Real-time Human Activity Recognition (HAR) has wide-ranging applications in areas such as context-aware environments, public safety, assistive technologies, and autonomous monitoring and surveillance systems. However, existing real-time HAR systems face significant challenges, including limited scalability and high computational costs arising from redundant features. To address these issues, the Inception-V3 model was customized with region-based and boundary-aware operations, using average pooling and max pooling, respectively, to enhance region homogeneity, suppress noise, and capture discriminative local features, while improving robustness through down-sampling. Furthermore, to effectively encode motion dynamics, an Attention-Augmented Long Short-Term Memory (AA-LSTM) network was employed to learn temporal dependencies across video frames. Features are extracted from video dataset and are then optimized through a novel proposed dynamic composite feature selection method called Adaptive Dynamic Fitness Sharing and Attention (ADFSA). This ADFSA mechanism is embedded within a genetic algorithm to select a compact, optimized subset of features by dynamically balancing multiple objectives, accuracy, redundancy reduction, feature uniqueness, and complexity minimization. As a result, the selected subset of diverse and discriminative features enables lightweight machine learning classifiers to achieve accurate and robust HAR in heterogeneous environments. Experimental results demonstrate up to 99.65\% accuracy using as few as seven selected features, with improved inference time on the challenging UCF-YouTube dataset, which includes factors such as occlusion, cluttered backgrounds, complex motion dynamics, and poor illumination conditions.
Authors: Haozhen Yan, Yan Hong, Suning Lang, Jiahui Zhan, Yikun Ji, Yujie Gao, Huijia Zhu, Jun Lan, Jianfu Zhang
Abstract: With generative models becoming increasingly sophisticated and diverse, detecting AI-generated images has become increasingly challenging. While existing AI-genereted Image detectors achieve promising performance on in-distribution generated images, their generalization to unseen generative models remains limited. This limitation is largely attributed to their reliance on generation-specific artifacts, such as stylistic priors and compression patterns. To address these limitations, we propose GAMMA, a novel training framework designed to reduce domain bias and enhance semantic alignment. GAMMA introduces diverse manipulation strategies, such as inpainting-based manipulation and semantics-preserving perturbations, to ensure consistency between manipulated and authentic content. We employ multi-task supervision with dual segmentation heads and a classification head, enabling pixel-level source attribution across diverse generative domains. In addition, a reverse cross-attention mechanism is introduced to allow the segmentation heads to guide and correct biased representations in the classification branch. Our method achieves state-of-the-art generalization performance on the GenImage benchmark, imporving accuracy by 5.8%, but also maintains strong robustness on newly released generative model such as GPT-4o.
Authors: Nikhil Keetha, Norman M\"uller, Johannes Sch\"onberger, Lorenzo Porzi, Yuchen Zhang, Tobias Fischer, Arno Knapitsch, Duncan Zauss, Ethan Weber, Nelson Antunes, Jonathon Luiten, Manuel Lopez-Antequera, Samuel Rota Bul\`o, Christian Richardt, Deva Ramanan, Sebastian Scherer, Peter Kontschieder
Abstract: We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions, and then directly regresses the metric 3D scene geometry and cameras. MapAnything leverages a factored representation of multi-view scene geometry, i.e., a collection of depth maps, local ray maps, camera poses, and a metric scale factor that effectively upgrades local reconstructions into a globally consistent metric frame. Standardizing the supervision and training across diverse datasets, along with flexible input augmentation, enables MapAnything to address a broad range of 3D vision tasks in a single feed-forward pass, including uncalibrated structure-from-motion, calibrated multi-view stereo, monocular depth estimation, camera localization, depth completion, and more. We provide extensive experimental analyses and model ablations demonstrating that MapAnything outperforms or matches specialist feed-forward models while offering more efficient joint training behavior, thus paving the way toward a universal 3D reconstruction backbone.
Authors: Yi Yang, Xiaokun Zhang, Qingchen Fang, Jing Liu, Ziqi Ye, Rui Li, Li Liu, Haipeng Wang
Abstract: Cross-modal artificial intelligence, represented by visual language models, has achieved significant success in general image understanding. However, a fundamental cognitive inconsistency exists between general visual representation and remote sensing image interpretation: remote sensing images couple topography, terrain, and spatial structure, thereby inherently requiring models to possess deep geoscientific understanding. This cognitive difference is further amplified in synthetic aperture radar (SAR) imagery: while SAR possesses irreplaceable all-weather, all-day observation capabilities, it is constrained by coherent imaging mechanisms, exhibiting significant modal heterogeneity with general images. To address this inconsistency, we propose FUSAR-KLIP, the first knowledge-guided general multimodal foundational model for SAR, along with reusable data and evaluation baselines. Specifically: (1) FUSAR-GEOVL-1M (the first large-scale SAR dataset with complete geographic projection attributes) was constructed, covering multiple satellite platforms, 120,000 images, and 135 cities; (2) Aligned structured text was generated through hierarchical cognitive thought chains, accurately encoding more than 1 million multidimensional semantic information from geomorphological environment and regional attributes to spatial relationships; (3) A self-consistent iterative optimization mechanism was designed to guide cross-modal learning with this knowledge information consistent with human cognition and physical laws in a self-supervised closed loop consisting of contrast, matching, and reconstruction; (4) A unified evaluation benchmark was established in 11 typical downstream tasks in the two major categories of vision and language, and compared with 15 mainstream foundation models.
Authors: Jiayao Jiang, Siran Peng, Bin Liu, Qi Chu, Nenghai Yu
Abstract: The rapid development of deepfake generation techniques necessitates robust face forgery detection algorithms. While methods based on Convolutional Neural Networks (CNNs) and Transformers are effective, there is still room for improvement in modeling the highly complex and non-linear nature of forgery artifacts. To address this issue, we propose a novel detection method based on the Kolmogorov-Arnold Network (KAN). By replacing fixed activation functions with learnable splines, our KAN-based approach is better suited to this challenge. Furthermore, to guide the network's focus towards critical facial areas, we introduce a Landmark-assisted Adaptive Kolmogorov-Arnold Network (LAKAN) module. This module uses facial landmarks as a structural prior to dynamically generate the internal parameters of the KAN, creating an instance-specific signal that steers a general-purpose image encoder towards the most informative facial regions with artifacts. This core innovation creates a powerful combination between geometric priors and the network's learning process. Extensive experiments on multiple public datasets show that our proposed method achieves superior performance.
Authors: Anantajit Subrahmanya, Chandrakanth Gudavalli, Connor Levenson, B. S. Manjunath
Abstract: Accurately modeling human mobility is critical for urban planning, epidemiology, and traffic management. In this work, we introduce Markovian Reeb Graphs, a novel framework that transforms Reeb graphs from a descriptive analysis tool into a generative model for spatiotemporal trajectories. Our approach captures individual and population-level Patterns of Life (PoLs) and generates realistic trajectories that preserve baseline behaviors while incorporating stochastic variability by embedding probabilistic transitions within the Reeb graph structure. We present two variants: Sequential Reeb Graphs (SRGs) for individual agents and Hybrid Reeb Graphs (HRGs) that combine individual with population PoLs, evaluated on the Urban Anomalies and Geolife datasets using five mobility statistics. Results demonstrate that HRGs achieve strong fidelity across metrics while requiring modest trajectory datasets without specialized side information. This work establishes Markovian Reeb Graphs as a promising framework for trajectory simulation with broad applicability across urban environments.
Authors: Chenfei Liao, Wensong Wang, Zichen Wen, Xu Zheng, Yiyu Wang, Haocong He, Yuanhuiyi Lyu, Lutao Jiang, Xin Zou, Yuqian Fu, Bin Ren, Linfeng Zhang, Xuming Hu
Abstract: Recent efforts to accelerate inference in Multimodal Large Language Models (MLLMs) have largely focused on visual token compression. The effectiveness of these methods is commonly evaluated by measuring the accuracy drop on existing MLLM benchmarks before and after compression. However, these benchmarks are originally designed to assess general perception and reasoning abilities, rather than the specific challenges posed by visual token compression, leading to a fundamental task mismatch. In this work, we uncover a counterintuitive yet consistent phenomenon: simple image downsampling outperforms many advanced visual token compression methods across multiple widely used benchmarks. Through a comprehensive empirical study spanning eight popular benchmarks and multiple state-of-the-art compression techniques, we show that (i) current benchmarks contain substantial noise (task-irrelevant samples) for evaluating visual token compression, and (ii) downsampling can act as an effective data filter that distinguishes between simple and difficult samples with respect to compression sensitivity. Motivated by these findings, we propose VTC-Bench, an evaluation framework that explicitly leverages downsampling as a discriminator to denoise existing benchmarks, enabling a fairer and more meaningful additional assessment of visual token compression methods.
Authors: Muhammad Tayyab Khan, Zane Yong, Lequn Chen, Wenhe Feng, Nicholas Yew Jin Tan, Seung Ki Moon
Abstract: Engineering drawings are fundamental to manufacturing communication, serving as the primary medium for conveying design intent, tolerances, and production details. However, interpreting complex multi-view drawings with dense annotations remains challenging using manual methods, generic optical character recognition (OCR) systems, or traditional deep learning approaches, due to varied layouts, orientations, and mixed symbolic-textual content. To address these challenges, this paper proposes a three-stage hybrid framework for the automated interpretation of 2D multi-view engineering drawings using modern detection and vision language models (VLMs). In the first stage, YOLOv11-det performs layout segmentation to localize key regions such as views, title blocks, and notes. The second stage uses YOLOv11-obb for orientation-aware, fine-grained detection of annotations, including measures, GD&T symbols, and surface roughness indicators. The third stage employs two Donut-based, OCR-free VLMs for semantic content parsing: the Alphabetical VLM extracts textual and categorical information from title blocks and notes, while the Numerical VLM interprets quantitative data such as measures, GD&T frames, and surface roughness. Two specialized datasets were developed to ensure robustness and generalization: 1,000 drawings for layout detection and 1,406 for annotation-level training. The Alphabetical VLM achieved an overall F1 score of 0.672, while the Numerical VLM reached 0.963, demonstrating strong performance in textual and quantitative interpretation, respectively. The unified JSON output enables seamless integration with CAD and manufacturing databases, providing a scalable solution for intelligent engineering drawing analysis.
Authors: Karthikeyan Chandra Sekaran, Markus Geisler, Dominik R\"o{\ss}le, Adithya Mohan, Daniel Cremers, Wolfgang Utschick, Michael Botsch, Werner Huber, Torsten Sch\"on
Abstract: Recent cooperative perception datasets have played a crucial role in advancing smart mobility applications by enabling information exchange between intelligent agents, helping to overcome challenges such as occlusions and improving overall scene understanding. While some existing real-world datasets incorporate both vehicle-to-vehicle and vehicle-to-infrastructure interactions, they are typically limited to a single intersection or a single vehicle. A comprehensive perception dataset featuring multiple connected vehicles and infrastructure sensors across several intersections remains unavailable, limiting the benchmarking of algorithms in diverse traffic environments. Consequently, overfitting can occur, and models may demonstrate misleadingly high performance due to similar intersection layouts and traffic participant behavior. To address this gap, we introduce UrbanIng-V2X, the first large-scale, multi-modal dataset supporting cooperative perception involving vehicles and infrastructure sensors deployed across three urban intersections in Ingolstadt, Germany. UrbanIng-V2X consists of 34 temporally aligned and spatially calibrated sensor sequences, each lasting 20 seconds. All sequences contain recordings from one of three intersections, involving two vehicles and up to three infrastructure-mounted sensor poles operating in coordinated scenarios. In total, UrbanIng-V2X provides data from 12 vehicle-mounted RGB cameras, 2 vehicle LiDARs, 17 infrastructure thermal cameras, and 12 infrastructure LiDARs. All sequences are annotated at a frequency of 10 Hz with 3D bounding boxes spanning 13 object classes, resulting in approximately 712k annotated instances across the dataset. We provide comprehensive evaluations using state-of-the-art cooperative perception methods and publicly release the codebase, dataset, HD map, and a digital twin of the complete data collection environment.
Authors: Yinqi Cai, Jichang Li, Zhaolun Li, Weikai Chen, Rushi Lan, Xi Xie, Xiaonan Luo, Guanbin Li
Abstract: Recent advances in deep generative models have made it easier to manipulate face videos, raising significant concerns about their potential misuse for fraud and misinformation. Existing detectors often perform well in in-domain scenarios but fail to generalize across diverse manipulation techniques due to their reliance on forgery-specific artifacts. In this work, we introduce DeepShield, a novel deepfake detection framework that balances local sensitivity and global generalization to improve robustness across unseen forgeries. DeepShield enhances the CLIP-ViT encoder through two key components: Local Patch Guidance (LPG) and Global Forgery Diversification (GFD). LPG applies spatiotemporal artifact modeling and patch-wise supervision to capture fine-grained inconsistencies often overlooked by global models. GFD introduces domain feature augmentation, leveraging domain-bridging and boundary-expanding feature generation to synthesize diverse forgeries, mitigating overfitting and enhancing cross-domain adaptability. Through the integration of novel local and global analysis for deepfake detection, DeepShield outperforms state-of-the-art methods in cross-dataset and cross-manipulation evaluations, achieving superior robustness against unseen deepfake attacks. Code is available at https://github.com/lijichang/DeepShield.
Authors: Md. Mohaiminul Islam, Md. Mofazzal Hossen, Maher Ali Rusho, Nahiyan Nazah Ridita, Zarin Tasnia Shanta, Md. Simanto Haider, Ahmed Faizul Haque Dhrubo, Md. Khurshid Jahan, Mohammad Abdul Qayum
Abstract: This study deliberates on the application of advanced AI techniques for brain tumor classification through MRI, wherein the training includes the present best deep learning models to enhance diagnosis accuracy and the potential of usability in clinical practice. By combining custom convolutional models with pre-trained neural network architectures, our approach exposes the utmost performance in the classification of four classes: glioma, meningioma, pituitary tumors, and no-tumor cases. Assessing the models on a large dataset of over 7,000 MRI images focused on detection accuracy, computational efficiency, and generalization to unseen data. The results indicate that the Xception architecture surpasses all other were tested, obtaining a testing accuracy of 98.71% with the least validation loss. While presenting this case with findings that demonstrate AI as a probable scorer in brain tumor diagnosis, we demonstrate further motivation by reducing computational complexity toward real-world clinical deployment. These aspirations offer an abundant future for progress in automated neuroimaging diagnostics.
Authors: Maryam Eftekharifar, Churun Zhang, Jialiang Wei, Xudong Cao, Hossein Heidari
Abstract: We present a framework that pioneers the prediction of photochemical conversion in complex three-dimensionally printed objects, introducing a challenging new computer vision task: predicting dense, non-visual volumetric physical properties from 3D visual data. This approach leverages the largest-ever optically printed 3D specimen dataset, comprising a large family of parametrically designed complex minimal surface structures that have undergone terminal chemical characterisation. Conventional vision models are ill-equipped for this task, as they lack an inductive bias for the coupled, non-linear interactions of optical physics (diffraction, absorption) and material physics (diffusion, convection) that govern the final chemical state. To address this, we propose Coupled Physics-Gated Adaptation (C-PGA), a novel multimodal fusion architecture. Unlike standard concatenation, C-PGA explicitly models physical coupling by using sparse geometrical and process parameters (e.g., surface transport, print layer height) as a Query to dynamically gate and adapt the dense visual features via feature-wise linear modulation (FiLM). This mechanism spatially modulates dual 3D visual streams-extracted by parallel 3D-CNNs processing raw projection stacks and their diffusion-diffraction corrected counterparts allowing the model to recalibrate its visual perception based on the physical context. This approach offers a breakthrough in virtual chemical characterisation, eliminating the need for traditional post-print measurements and enabling precise control over the chemical conversion state.
Authors: Wenyi Xiong, Jian Chen, Ziheng Qi, Wenhua Chen
Abstract: Trajectory prediction is crucial for the reliability and safety of autonomous driving systems, yet it remains a challenging task in complex interactive scenarios due to noisy trajectory observations and intricate agent interactions. Existing methods often struggle to filter redundant scene data for discriminative information extraction, directly impairing trajectory prediction accuracy especially when handling outliers and dynamic multi-agent interactions. In response to these limitations, we present a novel map-free trajectory prediction method which adaptively eliminates redundant information and selects discriminative features across the temporal, spatial, and frequency domains, thereby enabling precise trajectory prediction in real-world driving environments. First, we design a MoE based frequency domain filter to adaptively weight distinct frequency components of observed trajectory data and suppress outlier related noise; then a selective spatiotemporal attention module that reallocates weights across temporal nodes (sequential dependencies), temporal trends (evolution patterns), and spatial nodes to extract salient information is proposed. Finally, our multimodal decoder-supervised by joint patch level and point-level losses generates reasonable and temporally consistent trajectories, and comprehensive experiments on the large-scale NuScenes and Argoverse dataset demonstrate that our method achieves competitive performance and low-latency inference performance compared with recently proposed methods.
Authors: Fengli Wu, Vaidehi Patil, Jaehong Yoon, Yue Zhang, Mohit Bansal
Abstract: Pretrained Multimodal Large Language Models (MLLMs) are increasingly used in sensitive domains such as medical AI, where privacy regulations like HIPAA and GDPR require specific removal of individuals' or institutions' data. This motivates machine unlearning, which aims to remove the influence of target data from a trained model. However, existing unlearning benchmarks fail to reflect the hierarchical and multimodal structure of real-world medical data, limiting their ability to properly evaluate unlearning in practice. Therefore, we introduce MedForget, a hierarchy-aware multimodal unlearning benchmark that models hospital data as a nested structure, enabling fine-grained evaluation of multimodal unlearning across retain and forget splits. Experiments with current unlearning methods show that existing approaches struggle to achieve effective hierarchy-aware forgetting without degrading downstream medical utility. To address this limitation, we propose Cross-modal Hierarchy-Informed Projection for unlearning (CHIP), a training-free, hierarchy-aware multimodal unlearning method that deletes information by selectively removing target-specific weight subspaces while preserving sibling-shared information. Experiments show that CHIP achieves the highest forget-retain performance gap across all hierarchy levels while maintaining competitive downstream utility compared to existing methods. Overall, MedForget provides a practical, HIPAA-aligned benchmark for evaluating structured multimodal unlearning for medical data, and CHIP offers an effective and general solution for hierarchy-aware forgetting that balances deletion with utility.
Authors: Xiang Fan, Sharath Girish, Vivek Ramanujan, Chaoyang Wang, Ashkan Mirzaei, Petr Sushko, Aliaksandr Siarohin, Sergey Tulyakov, Ranjay Krishna
Abstract: Prior approaches injecting camera control into diffusion models have focused on specific subsets of 4D consistency tasks: novel view synthesis, text-to-video with camera control, image-to-video, amongst others. Therefore, these fragmented approaches are trained on disjoint slices of available 3D/4D data. We introduce OmniView, a unified framework that generalizes across a wide range of 4D consistency tasks. Our method separately represents space, time, and view conditions, enabling flexible combinations of these inputs. For example, OmniView can synthesize novel views from static, dynamic, and multiview inputs, extrapolate trajectories forward and backward in time, and create videos from text or image prompts with full camera control. OmniView is competitive with task-specific models across diverse benchmarks and metrics, improving image quality scores among camera-conditioned diffusion models by up to 33\% in multiview NVS LLFF dataset, 60\% in dynamic NVS Neural 3D Video benchmark, 20\% in static camera control on RE-10K, and reducing camera trajectory errors by 4x in text-conditioned video generation. With strong generalizability in one model, OmniView demonstrates the feasibility of a generalist 4D video model. Project page is available at https://snap-research.github.io/OmniView/
Authors: Aref Farhadipour, Teodora Vukovic, Volker Dellwo, Petr Motlicek, Srikanth Madikeri
Abstract: Person identification systems often rely on audio, visual, or behavioral cues, but real-world conditions frequently result in missing or degraded modalities. To address this challenge, we propose a multimodal person identification framework that utilizes gesture as a situational enhancer to supplement traditional modalities like voice and face. Our model employs a unified hybrid fusion strategy, integrating both feature-level and score-level information to maximize representational richness and decision accuracy. Specifically, it leverages multi-task learning to process modalities independently, followed by cross-attention and gated fusion mechanisms. Finally, a confidence-weighted strategy dynamically adapts to missing data, ensuring that our single classification head achieves optimal performance even in unimodal and bimodal scenarios. We evaluate our method on CANDOR, a newly introduced interview-based multimodal dataset, which we benchmark in this work for the first time. Our results demonstrate that the proposed trimodal system achieves 99.51% Top-1 accuracy on person identification tasks. In addition, we evaluate our model on the VoxCeleb1 dataset as a benchmark and reach 99.92% accuracy in bimodal mode, outperforming conventional approaches. Moreover, we show that our system maintains high accuracy even when one or two modalities are unavailable, making it a robust solution for real-world person recognition applications. The code and data for this work are publicly available.
Authors: Weichen Fan, Haiwen Diao, Quan Wang, Dahua Lin, Ziwei Liu
Abstract: Deep representations across modalities are inherently intertwined. In this paper, we systematically analyze the spectral characteristics of various semantic and pixel encoders. Interestingly, our study uncovers a highly inspiring and rarely explored correspondence between an encoder's feature spectrum and its functional role: semantic encoders primarily capture low-frequency components that encode abstract meaning, whereas pixel encoders additionally retain high-frequency information that conveys fine-grained detail. This heuristic finding offers a unifying perspective that ties encoder behavior to its underlying spectral structure. We define it as the Prism Hypothesis, where each data modality can be viewed as a projection of the natural world onto a shared feature spectrum, just like the prism. Building on this insight, we propose Unified Autoencoding (UAE), a model that harmonizes semantic structure and pixel details via an innovative frequency-band modulator, enabling their seamless coexistence. Extensive experiments on ImageNet and MS-COCO benchmarks validate that our UAE effectively unifies semantic abstraction and pixel-level fidelity into a single latent space with state-of-the-art performance.
Authors: Lvmin Zhang, Shengqu Cai, Muyang Li, Chong Zeng, Beijia Lu, Anyi Rao, Song Han, Gordon Wetzstein, Maneesh Agrawala
Abstract: We present PFP, a neural network structure to compress long videos into short contexts, with an explicit pretraining objective to preserve the high-frequency details of single frames at arbitrary temporal positions. The baseline model can compress a 20-second video into a context at about 5k length, where random frames can be retrieved with perceptually preserved appearances. Such pretrained models can be directly fine-tuned as memory encoders for autoregressive video models, enabling long history memory with low context cost and relatively low fidelity loss. We evaluate the framework with ablative settings and discuss the trade-offs of possible neural architecture designs.
Authors: Andr\'es Bell-Navas, Jes\'us Garicano-Mena, Antonella Ausiello, Soledad Le Clainche, Mar\'ia Villalba-Orero, Enrique Lara-Pezzi
Abstract: Introduction: Heart failure with preserved ejection fraction (HFpEF) arises from diverse comorbidities and progresses through prolonged subclinical stages, making early diagnosis and prognosis difficult. Current echocardiography-based Artificial Intelligence (AI) models focus primarily on binary HFpEF detection in humans and do not provide comorbidity-specific phenotyping or temporal estimates of disease progression towards decompensation. We aimed to develop a unified AI framework, CardioMOD-Net, to perform multiclass diagnosis and continuous prediction of HFpEF onset directly from standard echocardiography cine loops in preclinical models. Methods: Mouse echocardiography videos from four groups were used: control (CTL), hyperglycaemic (HG), obesity (OB), and systemic arterial hypertension (SAH). Two-dimensional parasternal long-axis cine loops were decomposed using Higher Order Dynamic Mode Decomposition (HODMD) to extract temporal features for downstream analysis. A shared latent representation supported Vision Transformers, one for a classifier for diagnosis and another for a regression module for predicting the age at HFpEF onset. Results: Overall diagnostic accuracy across the four groups was 65%, with all classes exceeding 50% accuracy. Misclassifications primarily reflected early-stage overlap between OB or SAH and CTL. The prognostic module achieved a root-mean-square error of 21.72 weeks for time-to-HFpEF prediction, with OB and SAH showing the most accurate estimates. Predicted HFpEF onset closely matched true distributions in all groups. Discussion: This unified framework demonstrates that multiclass phenotyping and continuous HFpEF onset prediction can be obtained from a single cine loop, even under small-data conditions. The approach offers a foundation for integrating diagnostic and prognostic modelling in preclinical HFpEF research.
Authors: Yankai Jiang, Qiaoru Li, Binlu Xu, Haoran Sun, Chao Ding, Junting Dong, Yuxiang Cai, Xuhong Zhang, Jianwei Yin
Abstract: Recent research on medical MLLMs has gradually shifted its focus from image-level understanding to fine-grained, pixel-level comprehension. Although segmentation serves as the foundation for pixel-level understanding, existing approaches face two major challenges. First, they introduce implicit segmentation tokens and require simultaneous fine-tuning of both the MLLM and external pixel decoders, which increases the risk of catastrophic forgetting and limits generalization to out-of-domain scenarios. Second, most methods rely on single-pass reasoning and lack the capability to iteratively refine segmentation results, leading to suboptimal performance. To overcome these limitations, we propose a novel agentic MLLM, named IBISAgent, that reformulates segmentation as a vision-centric, multi-step decision-making process. IBISAgent enables MLLMs to generate interleaved reasoning and text-based click actions, invoke segmentation tools, and produce high-quality masks without architectural modifications. By iteratively performing multi-step visual reasoning on masked image features, IBISAgent naturally supports mask refinement and promotes the development of pixel-level visual reasoning capabilities. We further design a two-stage training framework consisting of cold-start supervised fine-tuning and agentic reinforcement learning with tailored, fine-grained rewards, enhancing the model's robustness in complex medical referring and reasoning segmentation tasks. Extensive experiments demonstrate that IBISAgent consistently outperforms both closed-source and open-source SOTA methods. All datasets, code, and trained models will be released publicly.
Authors: Zhongming Liu, Bingbing Jiang
Abstract: Attention mechanisms have become a core component of deep learning models, with Channel Attention and Spatial Attention being the two most representative architectures. Current research on their fusion strategies primarily bifurcates into sequential and parallel paradigms, yet the selection process remains largely empirical, lacking systematic analysis and unified principles. We systematically compare channel-spatial attention combinations under a unified framework, building an evaluation suite of 18 topologies across four classes: sequential, parallel, multi-scale, and residual. Across two vision and nine medical datasets, we uncover a "data scale-method-performance" coupling law: (1) in few-shot tasks, the "Channel-Multi-scale Spatial" cascaded structure achieves optimal performance; (2) in medium-scale tasks, parallel learnable fusion architectures demonstrate superior results; (3) in large-scale tasks, parallel structures with dynamic gating yield the best performance. Additionally, experiments indicate that the "Spatial-Channel" order is more stable and effective for fine-grained classification, while residual connections mitigate vanishing gradient problems across varying data scales. We thus propose scenario-based guidelines for building future attention modules. Code is open-sourced at https://github.com/DWlzm.
Authors: Nahid Alam, Leema Krishna Murali, Siddhant Bharadwaj, Patrick Liu, Timothy Chung, Drishti Sharma, Akshata A, Kranthi Kiran, Wesley Tam, Bala Krishna S Vegesna
Abstract: Vision-language models (VLMs) have advanced rapidly, but their ability to capture spatial relationships remains a blindspot. Current VLMs are typically built with contrastive language-image pretraining (CLIP) style image encoders. The training recipe often flattens images into 1D patch sequences, discarding the 2D structure necessary for spatial reasoning. We argue that this lack of spatial awareness is a missing dimension in VLM design and a bottleneck for applications requiring spatial grounding, such as robotics and embodied AI. To address this, we investigate (i) image encoders trained with alternative objectives and (ii) 2D positional encodings. Our experiments show that these architectural choices can lead to improved spatial reasoning on several benchmarks.
Authors: Zhengxian Wu, Chuanrui Zhang, Shenao Jiang, Hangrui Xu, Zirui Liao, Luyuan Zhang, Huaqiu Li, Peng Jiao, Haoqian Wang
Abstract: Gait recognition is emerging as a promising technology and an innovative field within computer vision, with a wide range of applications in remote human identification. However, existing methods typically rely on complex architectures to directly extract features from images and apply pooling operations to obtain sequence-level representations. Such designs often lead to overfitting on static noise (e.g., clothing), while failing to effectively capture dynamic motion regions, such as the arms and legs. This bottleneck is particularly challenging in the presence of intra-class variation, where gait features of the same individual under different environmental conditions are significantly distant in the feature space. To address the above challenges, we present a Languageguided and Motion-aware gait recognition framework, named LMGait. To the best of our knowledge, LMGait is the first method to introduce natural language descriptions as explicit semantic priors into the gait recognition task. In particular, we utilize designed gait-related language cues to capture key motion features in gait sequences. To improve cross-modal alignment, we propose the Motion Awareness Module (MAM), which refines the language features by adaptively adjusting various levels of semantic information to ensure better alignment with the visual representations. Furthermore, we introduce the Motion Temporal Capture Module (MTCM) to enhance the discriminative capability of gait features and improve the model's motion tracking ability. We conducted extensive experiments across multiple datasets, and the results demonstrate the significant advantages of our proposed network. Specifically, our model achieved accuracies of 88.5%, 97.1%, and 97.5% on the CCPG, SUSTech1K, and CASIAB datasets, respectively, achieving state-of-the-art performance. Homepage: https://dingwu1021.github.io/LMGait/
Authors: Riccardo Catalini, Davide Di Nucci, Guido Borghi, Davide Davoli, Lorenzo Garattoni, Gianpiero Francesca, Yuki Kawana, Roberto Vezzani
Abstract: We introduce GazeD, a new 3D gaze estimation method that jointly provides 3D gaze and human pose from a single RGB image. Leveraging the ability of diffusion models to deal with uncertainty, it generates multiple plausible 3D gaze and pose hypotheses based on the 2D context information extracted from the input image. Specifically, we condition the denoising process on the 2D pose, the surroundings of the subject, and the context of the scene. With GazeD we also introduce a novel way of representing the 3D gaze by positioning it as an additional body joint at a fixed distance from the eyes. The rationale is that the gaze is usually closely related to the pose, and thus it can benefit from being jointly denoised during the diffusion process. Evaluations across three benchmark datasets demonstrate that GazeD achieves state-of-the-art performance in 3D gaze estimation, even surpassing methods that rely on temporal information. Project details will be available at https://aimagelab.ing.unimore.it/go/gazed.
Authors: Jing Zuo, Lingzhou Mu, Fan Jiang, Chengcheng Ma, Mu Xu, Yonggang Qi
Abstract: Achieving human-level performance in Vision-and-Language Navigation (VLN) requires an embodied agent to jointly understand multimodal instructions and visual-spatial context while reasoning over long action sequences. Recent works, such as NavCoT and NavGPT-2, demonstrate the potential of Chain-of-Thought (CoT) reasoning for improving interpretability and long-horizon planning. Moreover, multimodal extensions like OctoNav-R1 and CoT-VLA further validate CoT as a promising pathway toward human-like navigation reasoning. However, existing approaches face critical drawbacks: purely textual CoTs lack spatial grounding and easily overfit to sparse annotated reasoning steps, while multimodal CoTs incur severe token inflation by generating imagined visual observations, making real-time navigation impractical. In this work, we propose FantasyVLN, a unified implicit reasoning framework that preserves the benefits of CoT reasoning without explicit token overhead. Specifically, imagined visual tokens are encoded into a compact latent space using a pretrained Visual AutoRegressor (VAR) during CoT reasoning training, and the model jointly learns from textual, visual, and multimodal CoT modes under a unified multi-CoT strategy. At inference, our model performs direct instruction-to-action mapping while still enjoying reasoning-aware representations. Extensive experiments on LH-VLN show that our approach achieves reasoning-aware yet real-time navigation, improving success rates and efficiency while reducing inference latency by an order of magnitude compared to explicit CoT methods.
Authors: Thanh-Huy Nguyen, Hoang-Loc Cao, Dat T. Chung, Mai-Anh Vu, Thanh-Minh Nguyen, Minh Le, Phat K. Huynh, Ulas Bagci
Abstract: Scribble-supervised methods have emerged to mitigate the prohibitive annotation burden in medical image segmentation. However, the inherent sparsity of these annotations introduces significant ambiguity, which results in noisy pseudo-label propagation and hinders the learning of robust anatomical boundaries. To address this challenge, we propose SDT-Net, a novel dual-teacher, single-student framework designed to maximize supervision quality from these weak signals. Our method features a Dynamic Teacher Switching (DTS) module to adaptively select the most reliable teacher. This selected teacher then guides the student via two synergistic mechanisms: high-confidence pseudo-labels, refined by a Pick Reliable Pixels (PRP) mechanism, and multi-level feature alignment, enforced by a Hierarchical Consistency (HiCo) module. Extensive experiments on the ACDC and MSCMRseg datasets demonstrate that SDT-Net achieves state-of-the-art performance, producing more accurate and anatomically plausible segmentation.
Authors: Zhiyin Qian, Siwei Zhang, Bharat Lal Bhatnagar, Federica Bogo, Siyu Tang
Abstract: Human motion reconstruction from monocular videos is a fundamental challenge in computer vision, with broad applications in AR/VR, robotics, and digital content creation, but remains challenging under frequent occlusions in real-world settings. Existing regression-based methods are efficient but fragile to missing observations, while optimization- and diffusion-based approaches improve robustness at the cost of slow inference speed and heavy preprocessing steps. To address these limitations, we leverage recent advances in generative masked modeling and present MoRo: Masked Modeling for human motion Recovery under Occlusions. MoRo is an occlusion-robust, end-to-end generative framework that formulates motion reconstruction as a video-conditioned task, and efficiently recover human motion in a consistent global coordinate system from RGB videos. By masked modeling, MoRo naturally handles occlusions while enabling efficient, end-to-end inference. To overcome the scarcity of paired video-motion data, we design a cross-modality learning scheme that learns multi-modal priors from a set of heterogeneous datasets: (i) a trajectory-aware motion prior trained on MoCap datasets, (ii) an image-conditioned pose prior trained on image-pose datasets, capturing diverse per-frame poses, and (iii) a video-conditioned masked transformer that fuses motion and pose priors, finetuned on video-motion datasets to integrate visual cues with motion dynamics for robust inference. Extensive experiments on EgoBody and RICH demonstrate that MoRo substantially outperforms state-of-the-art methods in accuracy and motion realism under occlusions, while performing on-par in non-occluded scenarios. MoRo achieves real-time inference at 70 FPS on a single H200 GPU.
Authors: Erik Wallin, Lennart Svensson, Fredrik Kahl, Lars Hammarstrand
Abstract: In open-set semi-supervised learning (OSSL), we consider unlabeled datasets that may contain unknown classes. Existing OSSL methods often use the softmax confidence for classifying data as in-distribution (ID) or out-of-distribution (OOD). Additionally, many works for OSSL rely on ad-hoc thresholds for ID/OOD classification, without considering the statistics of the problem. We propose a new score for ID/OOD classification based on angles in feature space between data and an ID subspace. Moreover, we propose an approach to estimate the conditional distributions of scores given ID or OOD data, enabling probabilistic predictions of data being ID or OOD. These components are put together in a framework for OSSL, termed ProSub, that is experimentally shown to reach SOTA performance on several benchmark problems. Our code is available at https://github.com/walline/prosub.
Authors: Tyler J. Kovach, Daniel Schug, M. A. Wolfe, E. R. MacQuarrie, Patrick J. Walsh, Owen M. Eskandari, Jared Benson, Mark Friesen, M. A. Eriksson, Justyna P. Zwolak
Abstract: Semiconductor quantum dot (QD) devices have become central to advancements in spin-based quantum computing. However, the increasing complexity of modern QD devices makes calibration and control -- particularly at elevated temperatures -- a bottleneck to progress, highlighting the need for robust and scalable autonomous solutions. A major hurdle arises from trapped charges within the oxide layers, which induce random offset voltage shifts on gate electrodes, with a standard deviation of approximately 83 mV of variation within state-of-the-art present-day devices. Efficient characterization and tuning of large arrays of QD qubits depend on choices of automated protocols. Here, we introduce a physically intuitive framework for a bootstrapping, autonomous testing, and initialization system (BATIS) designed to streamline QD device evaluation and calibration. BATIS navigates high-dimensional gate voltage spaces, automating essential steps such as leakage testing, formation of all current channels, and gate characterization in the presence of trapped charges. For forming the current channels, BATIS follows a non-standard approach that requires a single set of measurements regardless of the number of channels. Demonstrated at 1.3 K on a quad-QD Si/Si$_x$Ge$_{1-x}$ device, BATIS eliminates the need for deep cryogenic environments during initial device diagnostics, significantly enhancing scalability and reducing setup times. By requiring only minimal prior knowledge of the device architecture, BATIS represents a platform-agnostic solution, adaptable to various QD systems, which bridges a critical gap in QD autotuning.
Authors: Yang Cao, Chengyue Gong, Yekun Ke, Xiaoyu Li, Yingyu Liang, Zhizhou Sha, Zhenmei Shi, Zhao Song
Abstract: The expressive power and computational complexity of deep visual generative models, such as flow-based and autoregressive (AR) models, have gained considerable interest for their wide-ranging applications in generative tasks. However, the theoretical characterization of their expressiveness through the lens of circuit complexity remains underexplored, particularly for the state-of-the-art architecture like FlowAR proposed by [Ren et al., 2024], which integrates flow-based and autoregressive mechanisms. This gap limits our understanding of their inherent computational limits and practical efficiency. In this study, we address this gap by analyzing the circuit complexity of the FlowAR architecture. We demonstrate that when the largest feature map produced by the FlowAR model has dimensions $n \times n \times c$, the FlowAR model is simulable by a family of threshold circuits $\mathsf{TC}^0$, which have constant depth $O(1)$ and polynomial width $\mathrm{poly}(n)$. This is the first study to rigorously highlight the limitations in the expressive power of FlowAR models. Furthermore, we identify the conditions under which the FlowAR model computations can achieve almost quadratic time. To validate our theoretical findings, we present efficient model variant constructions based on low-rank approximations that align with the derived criteria. Our work provides a foundation for future comparisons with other generative paradigms and guides the development of more efficient and expressive implementations.
Authors: Yang Cao, Xiaoyu Li, Yekun Ke, Yingyu Liang, Zhenmei Shi, Zhao Song
Abstract: A fundamental challenge in Visual Autoregressive models is the substantial memory overhead required during inference to store previously generated representations. Despite various attempts to mitigate this issue through compression techniques, prior works have not explicitly formalized the problem of KV-cache compression in this context. In this work, we take the first step in formally defining the KV-cache compression problem for Visual Autoregressive transformers. We then establish a fundamental negative result, proving that any mechanism for sequential visual token generation under attention-based architectures must use at least $\Omega(n^2 d)$ memory, when $d = \Omega(\log n)$, where $n$ is the number of tokens generated and $d$ is the embedding dimensionality. This result demonstrates that achieving truly sub-quadratic memory usage is impossible without additional structural constraints. Our proof is constructed via a reduction from a computational lower bound problem, leveraging randomized embedding techniques inspired by dimensionality reduction principles. Finally, we discuss how sparsity priors on visual representations can influence memory efficiency, presenting both impossibility results and potential directions for mitigating memory overhead.
Authors: Ziyao Shang, Misha Kaandorp, Kelly Payette, Marina Fernandez Garcia, Roxane Licandro, Georg Langs, Jordina Aviles Verdera, Jana Hutter, Bjoern Menze, Gregor Kasprian, Meritxell Bach Cuadra, Andras Jakab
Abstract: Magnetic resonance imaging (MRI) has played a crucial role in fetal neurodevelopmental research. Structural annotations of MR images are an important step for quantitative analysis of the developing human brain, with Deep Learning providing an automated alternative for this otherwise tedious manual process. However, segmentation performances of Convolutional Neural Networks often suffer from domain shift, where the network fails when applied to subjects that deviate from the distribution with which it is trained on. In this work, we aim to train networks capable of automatically segmenting fetal brain MRIs with a wide range of domain shifts pertaining to differences in subject physiology and acquisition environments, in particular shape-based differences commonly observed in pathological cases. We introduce a novel data-driven train-time sampling strategy that seeks to fully exploit the diversity of a given training dataset to enhance the domain generalizability of the trained networks. We adapted our sampler, together with other existing data augmentation techniques, to the SynthSeg framework, a generator that utilizes domain randomization to generate diverse training data. We ran thorough experimentations and ablation studies on a wide range of training/testing data to test the validity of the approaches. Our networks achieved notable improvements in the segmentation quality on testing subjects with intense anatomical abnormalities (p < 1e-4), though at the cost of a slighter decrease in performance in cases with fewer abnormalities. Our work also lays the foundation for future works on creating and adapting data-driven sampling strategies for other training pipelines.
Authors: Lei Wan, Prabesh Gupta, Andreas Eich, Marcel Kettelgerdes, Hannan Ejaz Keen, Michael Kl\"oppel-Gersdorf, Alexey Vinel
Abstract: Reliable perception remains a key challenge for Connected Automated Vehicles (CAVs) in complex real-world environments, where varying lighting conditions and adverse weather degrade sensing performance. While existing multi-sensor solutions improve local robustness, they remain constrained by limited sensing range, line-of-sight occlusions, and sensor failures on individual vehicles. This paper introduces VALISENS, a validated cooperative perception system that extends multi-sensor fusion beyond a single vehicle through Vehicle-to-Everything (V2X)-enabled collaboration between Connected Automated Vehicles (CAVs) and intelligent infrastructure. VALISENS integrates onboard and roadside LiDARs, radars, RGB cameras, and thermal cameras within a unified multi-agent perception framework. Thermal cameras enhances the detection of Vulnerable Road Users (VRUs) under challenging lighting conditions, while roadside sensors reduce occlusions and expand the effective perception range. In addition, an integrated sensor monitoring module continuously assesses sensor health and detects anomalies before system degradation occurs. The proposed system is implemented and evaluated in a dedicated real-world testbed. Experimental results show that VALISENS improves pedestrian situational awareness by up to 18% compared with vehicle-only sensing, while the sensor monitoring module achieves over 97% accuracy, demonstrating its effectiveness and its potential to support future Cooperative Intelligent Transport Systems (C-ITS) applications.
Authors: Yuxing Chen, Bowen Xiao, He Wang
Abstract: Due to the deformability of garments, generating a large amount of high-quality data for robotic garment manipulation tasks is highly challenging. In this paper, we present a synthetic garment dataset that can be used for robotic garment folding. We begin by constructing geometric garment templates based on keypoints and applying generative models to generate realistic texture patterns. Leveraging these keypoint annotations, we generate folding demonstrations in simulation and train folding policies via closed-loop imitation learning. To improve robustness, we propose KG-DAgger, which uses a keypoint-based strategy to generate demonstration data for recovering from failures. KG-DAgger significantly improves the model performance, boosting the real-world success rate by 25\%. After training with 15K trajectories (about 2M image-action pairs), the model achieves a 75\% success rate in the real world. Experiments in both simulation and real-world settings validate the effectiveness of our proposed framework.
Authors: Junyu Chen, Shuwen Wei, Joel Honkamaa, Pekka Marttinen, Hang Zhang, Min Liu, Yichao Zhou, Zuopeng Tan, Zhuoyuan Wang, Yi Wang, Hongchao Zhou, Shunbo Hu, Yi Zhang, Qian Tao, Lukas F\"orner, Thomas Wendler, Bailiang Jian, Benedikt Wiestler, Tim Hable, Jin Kim, Dan Ruan, Frederic Madesta, Thilo Sentker, Wiebke Heyer, Lianrui Zuo, Yuwei Dai, Jing Wu, Jerry L. Prince, Harrison Bai, Yong Du, Yihao Liu, Alessa Hering, Reuben Dorent, Lasse Hansen, Mattias P. Heinrich, Aaron Carass
Abstract: Medical image challenges have played a transformative role in advancing the field, catalyzing innovation and establishing new performance benchmarks. Image registration, a foundational task in neuroimaging, has similarly advanced through the Learn2Reg initiative. Building on this, we introduce the Large-scale Unsupervised Brain MRI Image Registration (LUMIR) challenge, a next-generation benchmark for unsupervised brain MRI registration. Previous challenges relied upon anatomical label maps, however LUMIR provides 4,014 unlabeled T1-weighted MRIs for training, encouraging biologically plausible deformation modeling through self-supervision. Evaluation includes 590 in-domain test subjects and extensive zero-shot tasks across disease populations, imaging protocols, and species. Deep learning methods consistently achieved state-of-the-art performance and produced anatomically plausible, diffeomorphic deformation fields. They outperformed several leading optimization-based methods and remained robust to most domain shifts. These findings highlight the growing maturity of deep learning in neuroimaging registration and its potential to serve as a foundation model for general-purpose medical image registration.
Authors: Zeyu Huang, Wei Meng, Quan Liu, Kun Chen, Li Ma
Abstract: Spiking neural networks offer low energy consumption due to their event-driven nature. Beyond binary spike outputs, their intrinsic floating-point dynamics merit greater attention. Neuronal threshold levels and reset modes critically determine spike count and timing. Hard reset cause information loss, while soft reset apply uniform treatment to neurons. To address these issues, we design an adaptive reset neuron that establishes relationships between inputs, outputs, and reset, while integrating a simple yet effective threshold adjustment strategy. Experimental results demonstrate that our method achieves excellent performance while maintaining lower energy consumption. In particular, it attains state-of-the-art accuracy on Tiny-ImageNet and CIFAR10-DVS. Codes are available at https://github.com/2ephyrus/AR-LIF.
Authors: Zhao Wang, Wei Dai, Thuy Thanh Dao, Steffen Bollmann, Hongfu Sun, Craig Engstrom, Shekhar S. Chandra
Abstract: Accurate magnetic resonance imaging (MRI) segmentation is crucial for clinical decision-making, but remains labor-intensive when performed manually. Convolutional neural network (CNN) based methods can be accurate and efficient but often generalize poorly to MRI variable contrast, intensity inhomogeneity, and sequences. Although the transformer-based Segment Anything Model (SAM) has demonstrated remarkable generalizability in natural images, existing adaptations often treat MRI as another imaging modality, overlooking these modality-specific challenges. We present SAMRI, an MRI-specialized SAM trained and validated on 1.1 million labeled MR slices spanning whole-body organs and pathologies. We demonstrate that SAM can be effectively adapted to MRI by fine-tuning its mask decoder using a two-stage strategy, reducing training time by 94 percent and trainable parameters by 96 percent compared to full-model retraining. Across diverse MRI segmentation tasks, SAMRI achieves a mean Dice of 0.87, delivering state-of-the-art accuracy across anatomical regions and robust generalization on unseen structures, particularly small clinically important structures. In addition, we provide a complete training-to-inference pipeline and a user-friendly local graphical interface that enables interactive application of pretrained SAMRI models on standard machines, facilitating practical deployment for real-world MRI segmentation.