paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

ReACT-CLIP: Response-Aware Test-Time Defense for Vision--Language Models

Hashmat Shadab Malik, Toluwani Aremu, Samuele Poppi, Muzammal Naseer, Salman Khan

Training-free test-time defenses offer a practical way to improve the adversarial robustness of CLIP-style vision--language models without modifying the pretrained model. However, their correction strength is typically fixed for a narrow range of attack budgets, even though the attack budget is unknown at inference and the required correction varies across samples. We show that this mismatch causes existing defenses to degrade sharply as attacks strengthen. We introduce ReACT-CLIP, a response-conditioned test-time defense that separately determines how strongly each input should be corrected and whether defensive intervention is necessary. Our key observation is that the relative increase in CLIP visual-feature drift between low- and high-noise probes provides a graded, sample-specific proxy for correction demand. ReACT-CLIP maps this relative cross-noise drift to the Gaussian noise scale used to construct a stable, noise-averaged feature anchor, enabling the corrective reach to adapt to each input. To determine whether intervention is necessary, we further observe that clean inputs retain stable class-probability distributions under weak spatial augmentations, whereas adversarial inputs exhibit greater variation. ReACT-CLIP quantifies this variation using a prediction-instability score computed by Jensen--Shannon divergence and combines it with relative cross-noise drift to form the defensive intervention score. ReACT-CLIP requires no model or prompt training, and its correction-strength mapping is calibrated once and fixed across datasets and attack budgets. Across 12 downstream datasets, as well as ImageNet and its distribution-shifted variants, ReACT-CLIP delivers substantial robustness gains across diverse attack types and strengths while largely preserving clean accuracy.

arXiv

DocPO: Advancing Document Policy Optimization via Tailored Step-Aware Rewards

YUNHAO WANG, Binghong Wu, Zhenyu Huang, Jiacheng Shi, Shuo Huang, TingHao YU, Feng Zhang

Reinforcement learning (RL) for document parsing often relies on reference-based rewards rooted in edit distance (e.g., tree edit distance), yet it remains hard to optimize in the high-accuracy regime because such rewards become weakly discriminative: near-correct outputs receive very similar scores, providing limited learning signal for hard cases. We propose Step-Aware Annealing (SAA), a plug-and-play reward sharpening mechanism that progressively increases reward curvature during training, amplifying subtle quality differences among high-scoring samples while preserving stability in early learning. Built on SAA, we introduce DocPO, a document policy optimization framework with element-specific, reference-based rewards anchored by edit-distance signals: normalized string edit distance (NED) for text, tree edit distance similarity (TEDS) for tables, and a hybrid Rubric+edit reward for formulas. Experiments on OmniDocBench and DocElemHard show that SAA consistently improves GRPO-style RL across document elements over non-annealed rewards, without requiring additional human supervision for reward construction.

arXiv

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Haodong LI, Tianfei Ren, Xiaoxiao Ma, Chunmei Qing, Zhen Fang, Sipeng He, Ziyu Guo, Haoyu Wu, Juanxi Tian, Yihang Zou, Ruichuan An, Dongzhi Jiang, Boxue Yang, Ji Xie, Xu Huang, Wenhao Yan, Jialv Zou, Zhengrong Yue, Yaxin Luo, Xiaotong Li, Yuzhu Wang, Junyan Ye, Jinjing Zhao, Zehui Chen, Lin Chen, Renye Yan, Feng Zhao, Pheng-Ann Heng

Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be inferred implicitly from a highly compressed text prompt. Existing chain-of-thought approaches introduce intermediate plans or visual states, but these representations are typically non-executable or temporally sparse, limiting their ability to instantiate and control the complete spatiotemporal process. To address this limitation, we introduce VideoCoCo, an agentic dual-engine framework in which executable Blender code serves as a process-level chain of thought. Given a text prompt, a coding agent synthesizes a Blender program that explicitly specifies the scene and its temporal evolution. The executable simulation engine runs the program to produce a deterministic spatiotemporal draft, which is subsequently transformed into a photorealistic video by a generative video engine through draft-conditioned editing. This decomposition separates process-level reasoning from high-fidelity visual realization. To adapt the video editor to simulated drafts, we construct VideoCoCo-3K, a curated dataset of draft-instruction-target triplets. VideoCoCo improves the OmniWeaving baseline from 0.475 to 0.558 on PhyGenBench and from 52.18 to 77.88 on VBench-2.0, achieving the best average score on both benchmarks. These results demonstrate that executable code provides an effective, controllable, and inspectable intermediate representation for physically consistent video generation.

arXiv

Data Pyramid for Embodied Manipulation: A Survey

Yifan Ye, Yankai Fu, Yaoxu Lv, Bohan Hou, Jun CEN, Lingdong Kong, Duo Zheng, Tianxing Chen, Jiaming Liu, Ziang Cao, Yunfan Lou, Wei Chow, Xian Sun, Yingshuo Wang, Kuangzhi Ge, Xiaowei Chi, Xidong Zhang, Zhibo Pang, Yiwu Zhong, Sirui Han, Zhihe Lu, Weihao Yuan, Qifeng Chen, Michael Yu Wang, Yao Mu, Ziwei Liu, Jianfei Yang, Ping Luo, Shanghang Zhang

Multimodal foundation models learned to see and to speak by consuming the whole internet. Embodied agents admit no such shortcut, since they require data that couple observations with physical states and actions. These signals can be provided, to varying degrees, by multiple data sources. In this work, we organize the embodied data ecosystem as a "pyramid" spanning five complementary sources: real-robot data, UMI-style data, egocentric and exocentric data, simulation data, and general vision-language data. We organize the pyramid around the tension between scalability and robot alignment, and further characterize each source in terms of data quality, diversity, reusability, and physical fidelity. We then analyze recent embodied foundation models through the lens of their data recipes, examining how different sources are selected, aligned, and mixed during pretraining. For embodied brain models, vision-language-action models, and world-action models alike, we relate data composition to capabilities in perception, reasoning, planning, action generation, and world prediction. We close by discussing six open challenges: building large-scale tactile datasets, collecting failure and recovery data, developing scalable data-collection pipelines, aligning actions across embodiments, leveraging egocentric data for dexterous manipulation, and designing principled data recipes for robot learning. We hope this work paves the foundation for the design of next-generation embodied systems.

arXiv

Attributes Should Come from Images, Not Class Names: Distribution-Conditioned Attribute Selection for Vision-Language Models

Gautam Rajendrakumar Gare, Jia Shi, Zhiqiu Lin, Deepak Pathak, John Galeotti, Deva Ramanan

A popular route to interpretable zero-shot classification asks a large language model (LLM) to describe each class name and prompts CLIP with the resulting descriptors. We show that these descriptors carry little visual evidence of their own: removing the class name from the prompt collapses ImageNet accuracy from 59.5% to 15.5%. The diagnosis is that the descriptors are conditioned on the label rather than on the images, so they describe the concept in general and mislead exactly when the data shifts; an LLM insists that strawberries are red, but every strawberry in ImageNet-Sketch is a colorless line drawing. We therefore select attributes from the target image collection instead: we score a large attribute pool against the images in CLIP's joint embedding space and keep the top-scoring attributes per class. Selected this way, class-name-free attribute prompts reach 23.8% on ImageNet (against 15.5% for LLM descriptors), the gain holds on four shifted ImageNet variants, and reselecting from the LLM's own pool isolates the selection mechanism as the cause. With one image per class, the selected attributes outperform the prompt-tuning method CoOp by 3 points while fitting in under a minute instead of 14 hours, with no learned soft prompt to obscure the decision. Because the attribute set is chosen by the data, it doubles as a readable summary of a dataset, which we use to describe distribution shift in words. Our code and results are available on our project page: https://ggare-cmu.github.io/AttributeSelect/

arXiv

Decouple and Reason: Anatomically Guided Two-Stage Voxel-Level Grounding of Free-Text Findings in 3D Chest CT

Kwang-Hyun Uhm, Inhwa Son, Sung-Jea Ko

Automatic voxel-level grounding of free-text findings in 3D chest Computed Tomography (CT) is critical for clinical interpretability. However, this task remains highly challenging due to the intricate spatial complexity of large 3D volumes and the heterogeneity of free-text findings. Existing end-to-end approaches often struggle to simultaneously learn the localized feature representations required for accurate 3D segmentation and the complex semantic understanding needed for text alignment, leading to suboptimal grounding performance. To overcome this fundamental limitation, we propose a novel decoupled framework that disentangles the problem into two specialized stages: (1) class-agnostic lesion segmentation and (2) text-volume reasoning. This structural separation allows the model to first extract candidate sub-volumes by localizing potential abnormalities. Subsequently, intensive cross-modal reasoning is performed to align these localized sub-volumes with free-text medical findings. To resolve the spatial ambiguities inherent in local regions, the reasoning module is augmented with explicit anatomical guidance, utilizing relative spatial coordinates and lung lobe priors. Evaluated on the ReXGroundingCT benchmark, our method achieves state-of-the-art performance in overall grounding quality on the official leaderboard. These results demonstrate that decoupling detection from reasoning is a highly effective paradigm for handling the complexity of 3D medical visual grounding. Our code is publicly available at https://github.com/khuhm/DAGG.

arXiv

Traj-VLN: Learning Pixel-Space Interaction via Autoregressive Trajectory Generation

Changfei Fu, Guangcheng Chen, Aoxiang Gu, Haoxiang Liang, Wenjun Xu, Hong Zhang

Benefiting from the powerful priors embedded in large-scale pre-training data and the emerging commonsense reasoning ability, large language models (LLMs) have shown unprecedented generalization capabilities in many research fields. Recently, projecting visual embeddings into the language space via vision-language models (VLMs) to achieve sim-toreal and cross-scene generalization has become a prevailing paradigm in the field of Vision-and-Language Navigation in Continuous Environments (VLN-CE). VLN requires an embodied agent to navigate through unseen environments following natural linguistic instructions. We emphasize that a VLN task can be decomposed into a sequence of sub-tasks, each corresponding to a process of 3D spatial interaction with the environments described by instructions such as "walk to the end of the sofa and turn left." However, such spatial interactions involving moving into the image along the direction of depth sensing are puzzling for VLMs as they were predominantly trained on conversations with RGB images. Rather than incorporating depth or 3D geometric information-which VLMs rarely encounter during pretrainingwe propose an alternative approach: fine-tuning VLMs to learn navigation interactions directly in 2D pixel space through autoregressive trajectory generation. Given a linguistic instruction and historical observations, our model sequentially predicts a series of pixel coordinates, drawing a trajectory from the bottom center of the current observation. While prior work has proved that pixel-goal supervision outperforms learning of discrete actions, our experiments further verify that the supervision of pixel-space trajectory significantly enhances VLN performance. Moreover, we demonstrate that our flagship model achieves state-of-the-art level performance with relatively limited computational resources and training data.

arXiv

LAVA: Layered Audio-Visual Anti-tampering Watermarking for Robust Deepfake Detection and Localization

Bokang Zeng, Zheng Gao, Xiaoyu Li, Xiaoyan Feng, Jiaojiao Jiang

Proactive watermarking offers a promising approach for deepfake tamper detection and localization in short-form videos. However, existing methods often decouple audio and visual evidence and assume that watermark signals remain reliable under real-world degradations, making tamper localization vulnerable to multimodal misalignment and compression distortions. Moreover, existing semi-fragile visual watermarking methods often degrade significantly under codec compression because their embedding bands overlap with compression-sensitive frequency regions. To address these limitations, we propose Layered Audio-Visual Anti-tampering Watermarking (LAVA), a calibration-aware audio-visual watermark fusion framework for deepfake tamper detection and localization. LAVA leverages cross-modal watermark fusion and calibration-aware alignment to preserve consistent and reliable tamper evidence under compression and audio-visual asynchrony, enabling robust tamper localization. Extensive experiments demonstrate that LAVA achieves near-perfect detection performance (AP = 0.999), remains robust to compression and multimodal misalignment, and significantly improves tamper localization reliability over existing audio-visual fusion baselines.

arXiv

Certainty Is Redundant: Token Sparsification for Efficient Camouflaged Object Detection with Vision Foundation Models

Yuhan Gao, Shuhao Kang, Xin He, Bing Li, Ming-Ming Cheng, Yun Liu

Camouflaged object detection (COD) aims to segment objects that closely resemble their surrounding environments. Vision foundation models (VFMs) provide strong transferable representations for COD, but their large-scale architectures and full-token processing incur substantial computational overhead. To address this issue, we propose Certainty-Aware Token Sparsification (CATS) for efficient VFM-based COD. Rather than estimating general token importance, CATS determines whether each token still requires deeper refinement according to its foreground--background certainty. It progressively terminates the independent updates of high-certainty tokens while retaining ambiguous tokens for further reasoning, thereby shortening the active token sequence across encoder stages. Since computational redundancy does not imply informational irrelevance, we further introduce Dual-Path Feature Compensation (DPFC), which separately compresses removed foreground and background tokens into compact certainty-weighted prototypes. Extensive experiments across multiple VFMs, backbone scales, COD architectures, and benchmark datasets show that our method significantly reduces computational cost with only marginal accuracy degradation, suggesting a favorable accuracy--efficiency trade-off for VFM-based COD. The code will be released.

arXiv

Controllable Video Object Insertion via Multi-View Priors

Qi Xia, Peishan Cong, Yichen Yao, Ziyi Wang, Yaoqin Ye, Yuexin Ma

Video object insertion places a user-specified object in an existing dynamic scene. Existing methods typically condition generation on text or a single reference image. Consequently, object appearance is underconstrained under viewpoint changes, often leading to identity drift, incorrect foreground-background layering, boundary artifacts, and temporal flickering. In this paper, we propose a video object insertion framework that incorporates multi-view object priors to address these limitations. The framework lifts a 2D reference image into a multi-view representation and uses view-consistent conditioning to provide stable identity guidance and view-adaptive appearance cues. A quality-aware weighting mechanism reduces the influence of noisy or imperfect reconstructed views. We further introduce an Integration-Aware Consistency Module that promotes plausible occlusion, clean boundaries, and temporal continuity. Experiments demonstrate that the proposed framework improves visual quality, controllability, identity consistency, and foreground-background integration for video object insertion compared to the baseline methods. Project page: https://polarisxq.github.io/MOVI/.

arXiv

PhyEdit: Towards Real-World Object Manipulation via Physically-Grounded Image Editing

Ruihang Xu, Dewei Zhou, Xiaolong Shen, Fan Ma, Yi Yang

Achieving physically accurate object manipulation in image editing is essential for its potential applications in interactive world models. However, existing visual generative models often fail at precise spatial manipulation, resulting in incorrect scaling and positioning of objects. This limitation primarily stems from the lack of explicit mechanisms to incorporate 3D geometry and perspective projection. To achieve accurate manipulation, we develop PhyEdit, an image editing framework that leverages explicit geometric simulation as contextual 3D-aware visual guidance. By combining this plug-and-play 3D prior with joint 2D--3D supervision, our method effectively improves physical accuracy and manipulation consistency. To support this method and evaluate performance, we present a real-world dataset, RealManip-40K, for 3D-aware object manipulation featuring paired images and depth annotations. We also propose ManipEval, a benchmark with multi-dimensional metrics to evaluate 3D spatial control and geometric consistency. Extensive experiments show that our approach outperforms existing methods, including strong closed-source models, in both 3D geometric accuracy and manipulation consistency.

arXiv

Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation

Hanshuai Cui, Zhiqing Tang, Zhi Yao, Fanshuai Meng, Weijia Jia, Wei Zhao

Autoregressive (AR) video diffusion models enable long-form video generation but remain expensive due to repeated multi-step denoising. Existing training-free acceleration methods rely on binary cache-or-recompute decisions, overlooking intermediate cases where direct reuse is too coarse yet full recomputation is unnecessary. Moreover, asynchronous AR schedules assign different noise levels to co-generated frames, yet existing methods process the entire valid interval uniformly. To address these AR-specific inefficiencies, we present SCOPE, a training-free framework for efficient AR video diffusion. SCOPE introduces a tri-modal scheduler over cache, predict, and recompute, where prediction via noise-level Taylor extrapolation fills the gap between reuse and recomputation with explicit stability controls backed by error propagation analysis. It further introduces selective computation that restricts execution to the active frame interval. On MAGI-1 and SkyReels-V2, SCOPE achieves up to 4.73x speedup while maintaining quality comparable to the original output, outperforming all training-free baselines.

arXiv

Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models

Issa Sugiura, Keito Sasagawa, Keisuke Nakao, Koki Maeda, Ziqi Yin, Zhishen Yang, Shuhei Kurita, Yusuke Oda, Ryoko Tokuhisa, Daisuke Kawahara, Naoaki Okazaki

Developing vision-language models (VLMs) that generalize across diverse tasks requires large-scale training datasets with diverse content. In English, such datasets are typically constructed by aggregating and curating numerous existing visual question answering (VQA) resources. However, this strategy does not readily extend to other languages, where VQA datasets remain limited in both scale and domain coverage. In this work, we introduce Jagle, the largest Japanese multimodal post-training dataset to date, comprising approximately 9.2 million instances across diverse tasks. Rather than relying on existing VQA datasets, we collect heterogeneous source data, including images, image-text pairs, and PDF documents, and generate VQA pairs through multiple strategies such as VLM-based QA generation, translation, and text rendering. Experiments demonstrate that a 2.2B model trained with Jagle surpasses InternVL3.5-2B in average score across ten Japanese evaluation tasks and comes within five points of Qwen3-VL-2B-Instruct. Moreover, combining Jagle with FineVision improves English performance over training with FineVision alone. These benefits generalize across model backbones and scales: LLM-jp-4-VL 9B beta, a 9B-scale model built on the Japanese-centric LLM-jp-4-8B-instruct, achieves Japanese performance comparable to Qwen3-VL-8B-Instruct. To facilitate reproducibility and future research, we release the dataset, models, and code.

arXiv

LineGraph2Road: Structural Graph Reasoning on Line Graphs for Road Network Extraction

Zhengyang Wei, Renzhi Jing, Yiyi He, Jenny Suckale

Extracting routable road networks from satellite imagery requires accurate topology recovery beyond pixel-level segmentation. Recent methods decompose the task into keypoint detection and connectivity prediction, but reliably inferring road connectivity under structural ambiguity remains challenging. Overpasses introduce non-planar crossings that can create false shortcuts, and occlusions break visual continuity, requiring long-range structural reasoning. We formulate road extraction as fully unobserved connectivity inference and construct a global but sparse Euclidean graph from detected keypoints to better leverage the long-term context. To improve link prediction, we transform this graph into its line graph and perform reasoning using a Graph Transformer. We propose an end-to-end pipeline that integrates vision-based segmentation, sparse graph construction, and structured inference. Our method explicitly models overpasses and uses topology-preserving vertex extraction to mitigate routing-critical errors. This approach achieves state-of-the-art performance on City-scale, SpaceNet, and Global-scale benchmarks in topology metrics including TOPO-F1 and APLS. In addition to quantitative gains, our method improves reconstruction of multi-level road structures crucial for real-world routing reliability. The code is available at: https://github.com/wzzzzzzy/LineGraph2Road.

arXiv

Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers

Hanshuai Cui, Zhiqing Tang, Qianli Ma, Zhi Yao, Weijia Jia, Wei Zhao

Diffusion Transformers (DiT) have emerged as a widely adopted backbone for high-fidelity image and video generation, yet their iterative denoising process incurs high computational costs. Existing training-free acceleration methods rely on feature caching and reuse under the assumption of temporal stability. However, reusing features for multiple steps may lead to latent drift and visual degradation. We observe that model outputs evolve smoothly along much of the diffusion trajectory, enabling principled predictions rather than naive reuse. Based on this insight, we propose \textbf{PrediT}, a training-free acceleration framework that formulates feature prediction as a linear multistep problem. We employ classical linear multistep methods to forecast future model outputs from historical information, combined with a corrector that activates in high-dynamics regions to prevent error accumulation. A dynamic step modulation mechanism adaptively adjusts the prediction horizon by monitoring the feature change rate. Together, these components enable substantial acceleration while preserving generation fidelity. Extensive experiments validate that our method achieves up to $5.54\times$ latency reduction across various DiT-based image and video generation models, while incurring negligible quality degradation.

arXiv

SARVLM: A Vision Language Foundation Model for Semantic Understanding in SAR Imagery

Qiwei Ma, Xukun Lu, Wang Liu, Puhong Duan, Xudong Kang, Shutao Li

Synthetic Aperture Radar (SAR) is a critical imaging modality due to its all-weather operational capability. Although recent advances in self-supervised learning and masked image modeling (MIM) have enabled SAR foundation models, these approaches primarily focus on low-level visual features and often neglect multi-modal representation. Moreover, multimodal data for SAR is scarce, limiting the development of robust cross-modal models. To address this limitation, we construct SARVLM-1M, a large-scale vision-language dataset comprising over one million image-text pairs aggregated from existing datasets. Furthermore, to mitigate the substantial differences between SAR and natural imagery, we propose a two-stage domain transfer training strategy that leverages optical remote sensing data as an intermediate bridge, facilitating effective knowledge transfer from natural images to SAR domains. Based on this strategy, we develop SARVLM, the first vision-language foundation model tailored for SAR, consisting of SARCLIP and SARCap. In addition, an ensemble strategy is utilized to improve the cross-scene generalization capability of the model. Moreover, SARDet and SARRot further validate the capability of the proposed framework in object detection. Extensive experiments on 13 benchmarks across image-text retrieval, target recognition, zero-shot classification, object detection, semantic localization, and image captioning demonstrate the superior feature extraction and interpretation capabilities of SARVLM. It consistently outperforms state-of-the-art vision-language models and advances semantic understanding in SAR imagery. Code and datasets will be released on https://github.com/KlayMa527/SARVLM.git.

arXiv

Adversarially Robust Few-Shot Anomaly Detection with Vision Foundation Models

Akib Mohammed Khan, Bartosz Krawczyk

Vision foundation models such as DINOv2 enable strong few-shot anomaly detection (FSAD) through simple non-parametric k-nearest-neighbor (k-NN) scoring over frozen patch features. Existing robust anomaly detection methods assume large normal-class training sets and adversarial training of the feature extractor. The few-shot regime, where the detector consists of a frozen backbone and a non-parametric scorer, has remained unaddressed despite its widespread deployment. We develop a white-box attack framework adapted to k-NN memory-bank detectors and introduce an adversarially robust FSAD method which is training-free with respect to the backbone. We introduce the DistanceProbe (DP), a lightweight MLP trained by regression to predict per-patch k-NN distance directly from frozen features, providing the differentiable proxy required for gradient-based attacks against non-parametric scorers. We further propose a two-level combined defense that operates using only the normal reference support set images. At the input level, PatchShift (PS) applies random pixel shifts to exploit the misalignment of adversarial perturbations with the encoder's patch grid, aggregating scores across multiple shifted views via element-wise median pooling. At the feature level we employ the FeaturePurifier (FP), a lightweight residual MLP trained on clean and adversarially augmented support features to project perturbed representations back toward the clean feature manifold. Through comprehensive experiments under various adversarial settings, we show that our method exhibits robust detection and localization with performance gains of ~27% image-level AUROC and ~51% pixel-level PRO over the undefended attacked baseline across MVTec-AD, VisA, and MPDD at k=4 shots, while preserving clean accuracy within 3%, matching full-shot adversarially-trained baselines on pixel-level AUROC, and holding under adaptive attack.

arXiv

Affordance-Guided Diffusion Prior for 3D Hand Reconstruction

Naru Suzuki, Takehiko Ohkawa, Tatsuro Banno, Jihyun Lee, Ryosuke Furuta, Yoichi Sato

How can we reconstruct 3D hand poses when large portions of the hand are heavily occluded by itself or by objects? Humans often resolve such ambiguities by leveraging contextual knowledge -- such as affordances, where an object's shape and function suggest how the object is typically grasped. Inspired by this observation, we propose a generative prior for hand pose refinement guided by affordance-aware textual descriptions of hand-object interactions (HOI). Our method employs a diffusion-based generative model that learns the distribution of plausible hand poses conditioned on affordance descriptions, which are inferred from a large vision-language model (VLM). This enables the refinement of occluded regions into more accurate and functionally coherent hand poses. Extensive experiments on HOGraspNet, a 3D hand-affordance dataset with severe occlusions, demonstrate that our affordance-guided refinement significantly improves hand pose estimation over both recent regression methods and diffusion-based refinement lacking contextual reasoning.

arXiv

SplitGaussian: Reconstructing Dynamic Scenes via Visual Geometry Decomposition

Lechao Cheng, Jiahui Li, Jingxuan He, Shengeng Tang, Gang Huang, Tianrui Hui, Yaxiong Wang, Zhun Zhong

Reconstructing dynamic 3D scenes from monocular video remains fundamentally challenging due to the need to jointly infer motion, structure, and appearance from limited observations. Existing dynamic scene reconstruction methods based on Gaussian Splatting often entangle static and dynamic elements in a shared representation, leading to motion leakage, geometric distortions, and temporal flickering. We identify that the root cause lies in the coupled modeling of geometry and appearance across time, which hampers both stability and interpretability. To address this, we propose SplitGaussian, a novel framework that explicitly decomposes scene representations into static and dynamic components. By decoupling motion modeling from background geometry and allowing only the dynamic branch to deform over time, our method prevents motion artifacts in static regions while supporting view- and time-dependent appearance refinement. This disentangled design not only enhances temporal consistency and reconstruction fidelity but also accelerates convergence. Extensive experiments demonstrate that our approach outperforms prior state-of-the-art methods in rendering quality, geometric stability, and motion separation.

arXiv

AQUA20: A Benchmark Dataset for Underwater Species Classification under Challenging Conditions

Taufikur Rahman Fuad, Sabbir Ahmed, Shahriar Ivan

Robust visual recognition in underwater environments remains a significant challenge due to complex distortions such as turbidity, low illumination, and occlusion, which severely degrade the performance of standard vision systems. This paper introduces AQUA20, a comprehensive benchmark dataset comprising 8,171 underwater images across 20 marine species reflecting real-world environmental challenges such as illumination, turbidity, occlusions, etc., providing a valuable resource for underwater visual understanding. Thirteen state-of-the-art deep learning models, including lightweight CNNs (SqueezeNet, MobileNetV2) and transformer-based architectures (ViT, ConvNeXt), were evaluated to benchmark their performance in classifying marine species under challenging conditions. Our experimental results show ConvNeXt achieving the best performance, with a Top-3 accuracy of 98.82% and a Top-1 accuracy of 90.69%, as well as the highest overall F1-score of 88.92% with moderately large parameter size. The results obtained from our other benchmark models also demonstrate trade-offs between complexity and performance. We also provide an extensive explainability analysis using GRAD-CAM and LIME for interpreting the strengths and pitfalls of the models. Our results reveal substantial room for improvement in underwater species recognition and demonstrate the value of AQUA20 as a foundation for future research in this domain. The dataset is publicly available at: https://huggingface.co/datasets/taufiktrf/AQUA20.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.