paperlist.ai

AI 顶会论文

AI 顶会论文库

检索 30+ 个顶会的论文，包括 NeurIPS、ICLR、ICML、CVPR、ACL、AAAI 等。输入关键词筛选，打开任意一篇查看摘要、作者和链接。

ECCV 2026

SV-TAD: Native Sparse Convolutions for Efficient Temporal Action Detection

Ricardo Ignacio Pizarro Carreño, Roberto Valle, José Buenaposada, Luis M. Bergasa, Luis Baumela

To adapt billion-parameter Vision Transformers for long-video understanding, recent methods freeze the backbone and train light-weight convolutional modules. While effective for parameter-efficient trai-ning, existing adapters do not reduce inference-time computation, leav-ing scalability with respect to video length largely unaddressed. Tokenselection can reduce attention cost by pruning redundant tokens, butit breaks the spatial grid structure required by convolutional adapters.This forces an expensive dense reconstruction, nullifying much of thepotential speedup. We address this by introducing native sparse 2D con-volutions, a primitive that allows these adapters, for the first time, tooperate directly and efficiently on dynamically pruned token sets. Weintegrate this primitive into SV-TAD, an adapter framework for tem-poral action detection, reducing VideoMAEv2-L computation by up to64% and achieving 2.2× faster inference, while maintaining state-of-the-art accuracy on THUMOS-14 and ActivityNet-1.3. When scaled toInternVideoNext-L, our approach surpasses the previous state of the artat roughly half its computational cost. Moreover, the sparse formulationnaturally supports auxiliary task tokens, which improves fine-grained as-sembly detection on ATTACH. Code and trained models are available athttps://github.com/pcr-upm/eccv26_tad.

ECCV 2026

StructSplat: Generalizable 3D Gaussian Splatting from Uncalibrated Sparse Views

Jia-Chen Zhao, Beiqi Chen, Xinyang Chen, Guangcong Wang, Liqiang Nie

We present StructSplat, a feed-forward and generalizable3D Gaussian reconstruction framework that operates directly on uncal-ibrated images without requiring camera parameters. Existing methodseither rely on per-scene optimization or assume known camera poses,and often entangle geometry and appearance within a unified backbone,limiting reconstruction fidelity and generalization. Our key idea is toadopt a structured representation that organizes geometry, seman-tic, and texture cues with explicit roles in the reconstruction process.Specifically, we introduce a pixel-aligned feature injection mechanismto enable accurate texture modeling from 2D observations, incorporatesemantic-aware priors to improve global consistency, and design a cameraalignment strategy to prevent information leakage and improve general-ization. Experiments show that our method significantly outperformsprior approaches on challenging benchmarks. On DL3DV, our methodachieves 28.045 PSNR, surpassing AnySplat (22.377) by +5.67 dB. Incross-dataset evaluation, our method achieves +1.94 dB over AnySplaton ACID and +1.72 dB on RealEstate10K.

ECCV 2026

StochasT: Learning with Stochastic Turn Depth for Visual Instruction Tuning

Yuan Qing, Chengzhi Mao, Boqing Gong

Large Vision-Language Models (LVLMs) rely extensively onVisual Instruction Tuning (VIT) to elicit their multimodal reasoning ca-pabilities. However, we find a discrepancy: VIT often packs multiple lan-guage tasks about the same image for conversational, multi-turn training,whereas existing benchmarks evaluate LVLMs in isolated, single-turn sce-narios. The models can suffer from visual attention decay and contextualoverfitting during multi-turn training, making it hard for them to realizetheir full potential in the mismatched test phase. To close the gap, wepropose learning with Stochastic Turn Depth (StochasT), which stochas-tically groups language tasks for the same image into clusters of vary-ing sizes (turn depth) while preserving their organic order. Hence, whileStochasT draws on Dropout and stochastic depth for ResNets, it doesnot actually drop anything to maximize the utility of the training data.Furthermore, we introduce a challenging, benchmark-agnostic evaluationmechanism based on the Balanced Latin Square to measure LVLMs’ ro-bustness under varying contextual dependencies. Extensive experimentsdemonstrate that StochasT effectively grants LVLMs strong, harmonizedcapabilities for both single-turn and multi-turn use cases. Code is avail-able at: https://yuanqing-ai.github.io/StochasT.

ECCV 2026

SEAR: Simple and Efficient Adaptation of Visual Geometric Transformers for RGB+Thermal 3D Reconstruction

Vsevolod Skorokhodov, Chenghao Xu, Shuo Sun, Olga Fink, Malcolm Mielle

Foundational feed-forward visual geometry models enableaccurate and efficient camera pose estimation and scene reconstruction bylearning strong scene priors from massive RGB datasets. However, theireffectiveness drops when applied to mixed sensing modalities, such asRGB-thermal (RGB-T) images. We observe that while a visual geometrygrounded transformer pretrained on RGB data generalizes well to thermal-only reconstruction, it struggles to align RGB and thermal modalitieswhen processed jointly. To address this, we propose SEAR, a simple yet ef-ficient fine-tuning strategy that adapts a pretrained geometry transformerto multimodal RGB-T inputs. Despite being trained on a relatively smallRGB-T dataset, our approach significantly outperforms state-of-the-artmethods for 3D reconstruction and camera pose estimation, achievingsignificant improvements over all metrics and delivering higher detailand consistency between modalities with negligible overhead in inferencetime compared to the original pretrained model. Notably, SEAR enablesreliable multimodal pose estimation and reconstruction even under chal-lenging conditions, such as low lighting and dense smoke. We validateour architecture through extensive ablation studies and demonstratehow the model aligns both modalities. Additionally, we introduce a newdataset featuring RGB and thermal sequences captured at different times,viewpoints, and illumination conditions, providing a robust benchmarkfor future work in multimodal 3D scene reconstruction. Code and modelsare publicly available at https://doi.org/10.5281/ZENODO.21077295.

ECCV 2026

RIGS: Radar-Informed Gaussian Splatting for Uncertainty-Aware 3D Occupancy and Motion Prediction

Zeyu Han, Junzhe Wu, Fang Zhang, Maani Ghaffari Jadidi, Jianqiang Wang

3D occupancy prediction provides dense semantic scene rep-resentations for autonomous driving, yet camera-only methods sufferfrom occlusion and adverse weather, while existing fusion approachestreat 4D radar as a generic point cloud and neglect its distinct physicalmeasurements. We propose RIGS, a radar-informed Gaussian splattingframework that systematically exploits 4D radar across three stages ofthe pipeline. In scene modeling, we extract range and power from the 4Dradar tensor for depth initialization and fuse them with images throughimage–radar–Gaussian tri-modal cross-attention. In occupancy refine-ment, we introduce evidential ellipsoidal BKI with anisotropic kernelsand use RCS power as physical existence evidence for adaptive false-positive filtering, yielding uncertainty-aware predictions with Dirichletepistemic and semantic uncertainty. In velocity estimation, we proposetemporal displacement-guided Doppler de-aliasing to recover high-speedradial velocities and complement tangential components, supervised bya multi-level loss over sparse radar points, dense voxels, and connectedcomponents. Experiments on K-Radar show that RIGS achieves stronglong-range occupancy among camera–radar methods with uncertainty-aware refinement and competitive velocity estimation, validated by sys-tematic incremental ablations.

ECCV 2026

Rethinking Prototype-based Similarity Learning for Few-Shot Object Detection

KunHo Heo, Seungjae Kim, Wongyu Lee, SuYeon Kim, MyeongAh Cho

Few-shot object detection aims to detect novel object cate-gories from only a few labeled examples, avoiding costly large-scale an-notation. Recent prototype-based similarity learning approaches enabletraining-free adaptation by matching query features with class proto-types. However, they suffer from two fundamental limitations: (i) classconfusion arising from inter-class similarity margin collapse, and (ii)insufficient visual cues for precise localization, as similarity scorescapture only class-level semantic affinity while providing limited spa-tial information. To address these issues, we introduce two complemen-tary components. Text-Anchored Semantic Mask (TSMa) lever-ages class-level text features as semantic anchors to identify semanti-cally aligned channels through channel-wise interaction between visualand text features. By suppressing style-induced spurious responses andemphasizing class-intrinsic signals, TSMa enlarges inter-class similar-ity margins and mitigates class confusion. We further propose Stage-Aligned Hierarchical Autoregressive Regression (SHARe), whichreformulates localization as a hierarchical autoregressive process thatprogressively refines bounding boxes across multiple stages. SHARe lever-ages the layer-wise characteristics of ViT representations by aligning fea-ture abstraction levels with regression stages: deeper layers guide earlycoarse localization, while shallower layers rich in edge and texture cuesrefine spatial details in later stages. Experiments on COCO demonstratea new state of the art, outperforming the previous best by +10.1 nAP,with extensive analysis validating each component. The code is availableat https://github.com/VisualScienceLab-KHU/ReSet.

ECCV 2026

RealDyadic: Synthesizing Realistic Dyadic 3D Dialogue with Neural Appearance Priors

Lei Zhu, Lijian Lin, Ye Zhu, Xuehan Hou, Jiahao Wu, Yu Li, Yunfei Liu, Jie Chen

Current audio-driven 3D head generation methods primarily focus on single-speaker scenarios, struggling to model natural, bidirectional conversational dynamics. Furthermore, extending these models to dyadic interactions relies heavily on 3D pseudo-labels derived from tracking algorithms. These labels inherently contain severe noise and fail to capture fine-grained facial dynamics, particularly accurate lip closure. To address these limitations, we propose RealDyadic, a two-stage framework that leverages 2D photometric supervision to refine and correct 3D motion priors. In the first stage, a diffusion-based transformer equipped with a dual-audio interaction module generates synchronized 3D facial motions from multi-speaker audio streams. In the second stage, a 3D Gaussian Splatting renderer projects these motions into high-fidelity 2D frames, enabling image-level gradients to backpropagate and penalize the inaccuracies of the initial 3D pseudo-labels via an alternating training strategy. Additionally, we introduce Real-Dialog, a dataset comprising over 50 hours of aligned 2D-3D dyadic conversational data across 500+ identities. Extensive experiments demonstrate that integrating 2D supervision into 3D motion generation significantly outperforms existing baselines in both lip-sync accuracy and conversational realism, explicitly overcoming the performance ceiling dictated by pseudo-label errors. The code is available at https://github.com/Pixel-Talk/RealDyadic.

ECCV 2026

ProSR: Semantic-Prototype-Guided Discrete Modeling for Physically Consistent SAR Super-Resolution

Byoungwoo Kim, Munchurl Kim

High-resolution Synthetic Aperture Radar (SAR) imageryis critical for precision analysis such as automatic target recognition,yet its acquisition is costly. Although generative image super-resolution(ISR) models offer a promising alternative, current smooth-approximation-based diffusion frameworks often struggle to preserve the coherent scat-tering statistics, causing stochastic structural distortions that are lessconsistent with real SAR physics. To address this, we propose Semantic-Prototype-Guided Super-Resolution (ProSR), reformulating SAR ISR asa semantically-guided discrete token prediction task within a quantizedlatent space. By mapping signal features to discrete scattering primitives,ProSR preserves the impulsive nature of SAR without over-smoothing.Furthermore, we integrate a Self-Supervised Learning backbone intoSAR ISR to extract label-free semantic priors, overcoming label scarcity.Guided by these priors, we introduce Semantic-Aligned Detail Encodingto decouple high-frequency signals into discrete scattering primitives. Inparallel, the Semantic Prototype Map Generator explicitly constructssemantic prototype maps, allowing Prototype-Map-Guided Attentionto route the information flows within identical categories and mitigateinter-class interference. To validate our approach, we present a large-scale0.25 m resolution benchmark from the Umbra Open Dataset. Experimen-tal results show ProSR achieves superior visual quality while preservingessential scattering characteristics required for practical SAR applications.

ECCV 2026

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

Thomas De Min, Subhankar Roy, Stephane Lathuiliere, Elisa Ricci, Massimiliano Mancini

E!ective collaboration begins with knowing when to ask forhelp. For example, when trying to identify an occluded object, a humanwould ask someone to remove the obstruction. Can MLLMs exhibit asimilar “proactive” behavior by requesting simple user interventions?To investigate this, we introduce ProactiveBench, a benchmark builtfrom seven repurposed datasets that tests proactiveness across di!erenttasks such as recognizing occluded objects, enhancing image quality, andinterpreting coarse sketches. We evaluate 22 MLLMs on ProactiveBench,showing that (i) they generally lack proactiveness; (ii) proactiveness doesnot correlate with model capacity; (iii) “hinting” at proactiveness yieldsonly marginal gains. Surprisingly, we found that conversation historiesand in-context learning introduce negative biases, hindering performance.Finally, we explore a simple fine-tuning strategy based on reinforcementlearning: its results suggest that proactiveness can be learned, evengeneralizing to unseen scenarios. We publicly release ProactiveBench asa first step toward building proactive multimodal models.

ECCV 2026

PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing

Shengbin Guo, Shaokang He, Chaoyue Meng, Shengpeng Xiao, Xunzhi Xiang, Shaofeng Zhang, Qi Fan

While instruction-based image editing, enabled by multi-modal generative models, has advanced significantly, existing bench-marks lack comprehensive evaluation of physics-based reasoning—a criti-cal capability for handling real-world scenarios. To address this, we intro-duce PhyEditBench, a benchmark designed to assess the physical under-standing of editing models. Guided by a hierarchical taxonomy, we estab-lish 4 primary classes and 12 subclasses. It comprises 238 high-quality,high-resolution, real-world instances—meticulously extracted fromvideos to capture authentic physical dynamics, alongside 35 syntheticAnti-Physics instances. Our empirical analysis of current SOTA editingmethods exposes substantial limitations in their physics-based reasoning.We further propose a training-free baseline named PhyWorld that usestest-time scaling and a latent reduction strategy. PhyWorld outperformscomparable models and suggests that the video generation process caneffectively serve as a reasoning mechanism for image editing. The projectpage is available at https://github.com/Previsior/PhyEditBench.

ECCV 2026

P²Fusion: Prompt-based Progressive Infrared-Visible Image Fusion via Dual-Prior Distillation

Yi Shi, Huichao Xie, Yuqing Wang, Mingyu Wang, Kaihui Yang, Yu Liu, Lu Ruitao, Lizhe Li, Junwei Han, Dingwen Zhang

Infrared-visible image fusion (IVIF) is pivotal for multimodalperception, yet reconciling the inherent information disparity betweenthermal and textural features remains a fundamental challenge. Exist-ing prior-guided methods often rely on static constraints that induceoptimization conflicts or utilize extrinsic semantic priors from large-scale foundation models (e.g., CLIP/DINO), which frequently fail toexploit the intrinsic modality characteristics essential for high-fidelityfusion. To address these issues, we propose P²Fusion, a prior-guideddistillation-based framework that reformulates IVIF via dual intrinsicprompts. Instead of imposing hard-coded penalties, we distill image-intrinsic priors, thermal saliency and spatial quality—into learnable,dynamic regulators. Specifically, a Teach-to-Fuse mechanism providesdual-granularity progressive guidance, coupled with a Gated DynamicExpert Recalibration (GDER) module for decoupled feature refinement.This design enables the network to adaptively mediate modal competi-tion through expert specialization. Extensive experiments demonstratethat P²Fusion achieves state-of-the-art performance across five main-stream datasets. Notably, our framework demonstrates consistent per-formance advantages in fusion quality, achieving state-of-the-art resultsin 14 out of 20 key evaluation metrics across 5 benchmarks. Further-more, it effectively contributes to the robustness of downstream percep-tion, such as +3.2% mAP on MSRS, +0.5% mAP on M3FD and +0.9%mAP on DroneVehicle for object detection. Our code will be available athttps://github.com/YiShi99/P2Fusion.

ECCV 2026

OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure

Chuancheng Shi, Wenhua Wu, Fei Shen, Xiaogang Zhu, Kun Hu, Zhiyong Wang

Text-to-image (T2I) models face significant safety risks fromadversarial induction, yet current concept erasure methods often causecollateral damage to benign attributes when suppressing selected neu-rons entirely. This occurs because sensitive and benign semantics ex-hibit non-orthogonal superposition, sharing activation subspaces wheretheir respective vectors are inherently entangled. To address this issue,we propose OrthoEraser, which leverages sparse autoencoders (SAE) toachieve high-resolution feature disentanglement and subsequently rede-fines erasure as an analytical orthogonalization projection that preservesthe benign manifold’s invariance. OrthoEraser first employs SAE to de-compose dense activations and segregate sensitive neurons. It then usescoupled neuron detection to identify non-sensitive features vulnerableto intervention. The key novelty lies in an analytical gradient orthog-onalization strategy that projects erasure vectors onto the null spaceof the coupled neurons. This orthogonally decouples the sensitive con-cepts from the identified critical benign subspace, effectively preservingnon-sensitive semantics. Experimental results on safety demonstrate thatOrthoEraser achieves high erasure precision, effectively removing harm-ful content while preserving the integrity of the generative manifold, andsignificantly outperforming SOTA baselines. WARNING: This papercontains results of unsafe models.

ECCV 2026

OmniX: From Unified Panoramic Generation and Perception To Graphics-Ready 3D Scenes

Yukun Huang, Jiwen Yu, Yanning Zhou, Jianan Wang, Xintao Wang, Pengfei Wan, Xihui Liu

There are two prevalent ways for automatic 3D scene con-struction: procedural generation and 2D lifting. Among these, panorama-based 2D lifting has emerged as a promising technique, leveraging pow-erful 2D generative priors to produce immersive, realistic, and diverse3D environments. In this work, we advance this technique to generategraphics-ready 3D scenes suitable for physically based rendering (PBR),relighting, and simulation. Our key insight is to repurpose 2D generativemodels for panorama perception of geometry, textures, and PBR mate-rials. Unlike existing 2D lifting approaches that emphasize appearancegeneration and neglect the perception of intrinsic properties, we presentOmniX, a versatile and unified framework for panorama generation, per-ception, and completion. Built upon cross-modal adapter structure andcyclic spatial operators, OmniX effectively repurposes pre-trained 2Dflow matching priors for joint modeling of multimodal, seamless equirect-angular representations. Furthermore, we construct a large-scale syn-thetic panorama dataset comprising high-quality multimodal panoramasfrom diverse indoor and outdoor scenes. Extensive experiments demon-strate the effectiveness and generality of OmniX as a unified frameworkfor panorama generation and perception across geometry, lighting, andsemantics, enabling graphics-ready 3D scene generation and opening newpossibilities for immersive and physically realistic virtual world creation.Project page is available at https://yukun-huang.github.io/OmniX/.

ECCV 2026

Noise is a Good Teacher: A Noise-Driven Framework for Robust Collaborative Perception

Chengyan Huang, Zhongxiang Zhao, Ziyao Zhang, Zihao Yang, Lin Wang

Collaborative perception mitigates occlusions and extendsthe perception range, yet its accuracy remains susceptible to both poseand feature noise. Given these limitations, we propose NoiseGT, anoise-driven framework built upon the principle that “Noise is a GoodTeacher”. Instead of treating noise as a disturbance, NoiseGT leveragesit as a self-supervised signal to enhance robustness at both the poseand feature levels. Specifically, a pose calibration module first appliesmulti-level noise injection, followed by graph-based alignment refinement.This process enables the module to learn pose-invariant alignment de-spite localization uncertainties. Meanwhile, a feature denoising moduleadopts a “high-noise-over-low-noise” strategy to inject high-magnitudenoise into bird’s-eye-view (BEV) features, guiding the denoiser towardnoise-robust representations without relying on clean intermediate super-vision. Together, these components form a noise-driven learning processthat promotes consistent fusion across agents. At the most challengingnoise setting ((σt , σr ) = (1.2 m, 1.2◦ )), NoiseGT achieves state-of-the-artperformance over previous methods, improving AP@0.5/0.7 by a rela-tive 12.03%/14.56% on V2X-Sim, 2.67%/0.89% on DAIR-V2X, and6.12%/9.69% on OPV2V. These results highlight the effectiveness andgenerality of noise-driven learning for robust collaborative perception.

ECCV 2026

Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification

Afshar Shamsi, Xiao-Yu Guo, Hamid Alinejad-Rokny, Arash Mohammadi, Damien Teney, Ehsan Abbasnejad

Test-Time Adaptation (TTA) seeks to improve model robust-ness under distribution shifts by adapting parameters using unlabeledtarget data. However, in the absence of supervision, entropy-based adap-tation is fundamentally underconstrained: multiple distinct parameterupdates can achieve similarly low entropy while inducing drasticallydifferent decision boundaries. This phenomenon, known as underspecifi-cation, renders standard TTA brittle and prone to collapse into spuriousmodes. In this work, we reinterpret TTA through a posterior-inspired lensinduced by entropy minimization, where low-entropy solutions define apseudo-likelihood over parameters. Instead of committing to a single pointestimate, we introduce a particle-based diversification framework thatexplores multiple plausible adaptation trajectories simultaneously. Ourmethod can be viewed as a structured exploration of multiple plausibleadaptation solutions, implemented through multi-level diversification atthe output, parameter, optimizer, and input levels. Crucially, the frame-work acts as a plug-and-play wrapper compatible with existing TTAmethods. Extensive experiments on challenging benchmarks demonstrateconsistent gains in stability and robustness, achieving improvements of3–4% under mixed shifts, 2–3% with batch size one, and 1–2.5% underlabel shifts, outperforming state-of-the-art baselines. Our results suggestthat treating TTA as a multi-hypothesis inference problem, rather thana single-point optimization task, is key to mitigating underspecificationand enabling reliable real-world deployment.

ECCV 2026

Meric: A Unified Framework for Multimodal Music Generation and Retrieval via Representation Space Anchoring

Xihua Wang, Yinbo Wang, Jingchao Zhang, Ruihua Song

Cross-modal music generation from text and visual inputsis uniquely challenging due to its subjective, one-to-many nature. Cur-rent methods face three major limitations: they are bottlenecked byscarce paired data, lack explicit one-to-many modeling, and isolate gen-eration from retrieval. To address these issues, we propose Meric, aunified framework for multimodal music generation and retrieval. Ourcore innovation is a music semantic anchor that decouples multimodalunderstanding from acoustic synthesis. We employ a two-stage train-ing pipeline. First, a Flow Matching decoder learns to synthesize audiofrom anchor embeddings using large, unpaired music corpora. Second, alightweight generative diffusion module maps multimodal inputs into thiscontinuous anchor space using limited paired data. This decoupled de-sign explicitly models cross-modal ambiguity and exploits unpaired datato bypass the paired data bottleneck. During inference, the predicted an-chor embedding simultaneously acts as a condition for acoustic synthesisand a query for music retrieval. Extensive experiments demonstrate thatMeric achieves state-of-the-art performance across text-to-music andvision-to-music generation and retrieval benchmarks.

ECCV 2026

MedGSSR: Generalizable Medical Image Super-Resolution 3D Reconstruction via Hierarchical Feed-forward Gaussian Splatting

Chengkai Wang, Luoyu Hong, Yiting Zhao, Jiamin Wang, Xiang Feng, Feiwei Qin, Zhenzhong Kuang, Xuefei Yin, Ali Bashashati, Yanming Zhu

High-resolution volumetric medical imaging is critical for clinical diagnosis, yet acquisition is often limited by scanner hardware, scan time, and for CT, radiation dose. Medical 3D Super-Resolution (Med3DSR) offers a computational alternative, but existing methods commonly rely on per-subject optimization, pretrained priors, or coordinatebased implicit representations, which compromise anatomical fidelity and limit efficiency. To address these limitations, we present MedGSSR, a fully end-to-end feed-forward framework that represents volumes as an explicit 3D Gaussian field for Med3DSR. Unlike coordinate-based implicit functions, our explicit 3D Gaussian representation naturally enhances signal continuity and local high-frequency fidelity. Specifically, MedGSSR explicitly decouples the reconstruction process into coarsegrained structural preservation and fine-grained textural refinement through the proposed Pyramid Anatomical Encoder and a Hierarchical Gaussian Projector. To support arbitrary-scale super-resolution, we introduce sub-voxel Gaussian decomposition and a Differentiable Gaussian Voxelizer that directly queries the continuous 3D intensity field, reducing discretization artifacts. Extensive experiments on MRI and CT benchmarks demonstrate that MedGSSR significantly outperforms state-ofthe-art methods. Notably, our framework exhibits robust generalizability across unseen datasets without requiring per-subject optimization, enabling fast inference and high-fidelity volumetric super-resolution in practical clinical settings. Our project webpage, including code, is at https://william2ai.github.io/medgssr

ECCV 2026

M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detection

Chao Wang, Wei Lu, Xiang Li, Jian Yang, Lei Luo

Single-source remote sensing object detection using opticalor SAR images struggles in complex environments. Optical images offerrich textural details but are often affected by low-light, cloud-obscured,or low-resolution conditions, reducing the detection performance. SARimages are robust to weather, but suffer from speckle noise and limitedsemantic expressiveness. Optical and SAR images provide complemen-tary advantages, and fusing them can significantly improve the detectionaccuracy. However, progress in this field is hindered by the lack of large-scale, standardized datasets. To address these challenges, we proposea new comprehensive dataset for optical-SAR fusion object detection,named Multi-resolution, Multi-polarization, Multi-scene, Multi-sourceSAR dataset (M4-SAR). It contains 112,174 instance-level aligned im-age pairs and nearly one million labeled instances with arbitrary orienta-tions, spanning six key categories. To enable standardized evaluation, wedevelop a unified benchmarking toolkit that integrates six state-of-the-art multi-source fusion methods. Additionally, we propose E2E-OSDet, anovel end-to-end multi-source fusion detection framework that mitigatescross-domain discrepancies and establishes a robust baseline for futurestudies. Extensive experiments on M4-SAR demonstrate that fusing op-tical and SAR data can improve mAP by 5.7% over single-source inputs,with particularly significant gains in complex environments.

ECCV 2026

Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding

Jiaqi Li, Shuntian Zheng, Yixian Shen, Jia-Hong Huang, Xiaoman Lu, Minzhe Ni, Yu Guan

Video Temporal Grounding (VTG) localizes the temporalboundaries of query-relevant moments in long, untrimmed videos, mak-ing video-language-model prohibitively expensive. While recent training-free token pruning has shown success in video question answering, naivelyapplying these objectives to VTG causes drastic degradation, as VTGcrucially depends on boundary-sensitive evidence and cross-frame rea-soning chains. We therefore identify two VTG-specific pruning principles:evidence retention, which keeps query-critical patches especially aroundevent boundaries, and connectivity strength, which preserves cross-frameconnectivity for long-range evidence aggregation. Building on these in-sights, we propose SemVID, a training-free pruning framework that con-structs a compact yet coherent token subset with complementary seman-tic roles. SemVID first allocates per-frame budgets by balancing queryrelevance and inter-frame variation to avoid over-pruned segments, andthen selects three types of tokens: object tokens for diverse query-criticalevidence, motion tokens to capture meaningful transitions and serve ascross-frame relays, and context tokens for scene continuity. Extensive ex-periments show that SemVID achieves a strong accuracy-efficiency trade-off, retaining up to 95.4% mIoU with only 12.5% visual tokens and de-livering up to a 5.8× prefill speedup, consistently outperforming priormethods under the same budgets. Our code is available here.

ECCV 2026

Intra-Class Consistency Guided Class-Agnostic Event Segmentation

Zhipeng Sui, Haiqing Hao, Weihua He, Wenhui Wang

Class-agnostic segmentation enables open-world object seg-mentation beyond predefined categories, and extending it to the eventdomain helps enhance perception in high-speed motion and extreme illu-mination scenarios. However, the sparsity and low redundancy of eventdata lead to weak intra-class consistency, making event-based segmen-tation typically underperform compared to RGB-based counterparts.To address this issue, we propose IC2 -ESeg, an Intra-class Consistencyguided, Class-agnostic Event Segmentation framework, including threemodules: intra-class consistency mining (ICM), lightweight informationinjection (LIJ), and cross-modal distillation (CMD). Grounded in theevent generation mechanism, the ICM module constructs noise, motion,and brightness representations by analyzing statistical noise frequency,spatio-temporal distribution, and brightness gradients, thereby enrichingthe informational content of event data. The LIJ module efficiently inte-grates these representations into the image encoder, while the CMD mod-ule transfers the general segmentation capability of Segment AnythingModel (SAM) to the event domain. Experiments on RGBE-SEG demon-strate that IC2 -ESeg achieves state-of-the-art (SOTA) performance inclass-agnostic segmentation. We also construct ComScene, a high reso-lution RGB-event segmentation dataset encompassing diverse scenarios.Results on MVSEC and ComScene demonstrate the strong generaliza-tion of IC2 -ESeg.

继续浏览

更多 AI 顶会论文

30+ 个顶会，按会议、年份和主题浏览。

浏览全部会议

进入任一会议和年份，查看完整论文列表。

全部会议 →

搜索论文

按标题、作者或关键词，在 21 万+ 篇论文里搜索。

搜索论文 →