ECCV 2026 论文列表

3D Gaussian Splatting (3DGS) has revolutionized fast novelview synthesis, yet its opacity-based formulation makes surface extrac-tion fundamentally difficult. Unlike implicit methods built on SignedDistance Fields or occupancy, 3DGS lacks a global geometric field, forc-ing existing approaches to resort to heuristics such as TSDF fusion ofblended depth maps. Inspired by the Objects as Volumes framework [38],we derive a principled occupancy field for Gaussian Splatting and showhow it can be used to extract highly accurate watertight meshes of com-plex scenes. Our key contribution is to introduce a learnable orientednormal at each Gaussian element and to define an adapted attenuationformulation, which leads to closed-form expressions for both the normaland occupancy fields at arbitrary locations in space. We further intro-duce a novel consistency loss and a dedicated densification strategy toenforce Gaussians to wrap the entire surface by closing geometric holes,ensuring a complete shell of oriented primitives. We modify the differen-tiable rasterizer to output depth as an isosurface of our continuous model,and introduce Primal Adaptive Meshing for Region-of-Interest mesh-ing at arbitrary resolution. We additionally expose fundamental biasesin standard surface evaluation protocols and propose two more rigor-ous alternatives. Overall, our method Gaussian Wrapping sets a newstate-of-the-art on DTU and Tanks and Temples, producing complete,watertight meshes at a fraction of the size of concurrent work—recoveringthin structures such as the notoriously elusive bicycle spokes. Our projectpage is available here.

Reconstructing and tracking dynamic 3D scenes is a funda-mental challenge in computer vision. Existing methods typically decou-ple geometry from motion: static multi-view reconstruction systems as-sume a rigid world, whereas dynamic tracking frameworks rely on explicitego-motion estimation or separate object motion models. In this work,we propose Flow4R, a unified framework that treats relative scene flowas the central representation linking 3D structure, camera ego-motion,and dynamic object motion. Given a two-view input, Flow4R employs ashared Vision Transformer to predict a compact, pixel-aligned propertyset comprising 3D point positions, scene flow, pose weights, and con-fidence maps. This flow-centric formulation allows local geometry andbidirectional motion to be jointly inferred in a single feedforward pass,eliminating the need for explicit pose regression heads or complex bundleadjustment. By training jointly on static and dynamic datasets, Flow4Rachieves state-of-the-art performance on 4D reconstruction and trackingbenchmarks, demonstrating the power of the flow-centric formulation forspatiotemporal scene understanding.

Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling diffusion models in visual generation. Recent advancements have focused on adaptively allocating computational resources across diverse tokens to improve efficiency and performance. However, we identify a routing assignment problem in existing diffusion MoE frameworks: the router fails to accurately allocate more computational resources to salient tokens. Our analysis attributes this failure to the router’s reliance on noise-corrupted latent features throughout the denoising process. Such stochastic noise obscures the critical structural and textural information, thereby preventing the router from effectively distinguishing salient tokens. To address this, we propose SharpMoE, a post-training framework with a saliency-harnessing accurate routing mechanism, which utilizes clean latent features as a noise-free guidance signal for routing. By bypassing the noise-distorted inputs, SharpMoE provides the router with clear saliency guidance, enabling the identification of salient tokens even in high-noise stages. Furthermore, we introduce a trajectory routing loss to constrain the compute allocation throughout the multi-step denoising trajectory, ensuring precise resource allocation along the generation rollout. Extensive experiments demonstrate that SharpMoE serves as a versatile, plug-and-play solution that further enhances the pretrained, converged MoE models, achieving stateof-the-art performance in visual generation.

Automatically retrieving videos from large camera-trap data-sets remains challenging. Text-to-Video retrieval (TVR) methods basedon large video-language models (VLMs) have potential to retrieve eventsof interest by describing them with simple text queries. However, cur-rent methods often lack spatiotemporal understanding and do not gen-eralize well to ecological data. In this work, we introduce Prompting-MammAlps, the first camera-trap TVR benchmark, and propose a fine-grained and interpretable TVR method. Specifically, we trained a vi-sion transformer to perform spatiotemporal action localization, and con-vert its output to structured text, describing each video. Independently,ethology-inspired queries are processed by a Large-Language Model (LLM)based coding agent to parse the structured text per video and retrievevideos accordingly. We harnessed the LLM to use functions from a cus-tom parsing library to minimize the risk of LLM hallucinations and toimprove method interpretability. This retrieval approach applied on thePrompting-MammAlps benchmark achieved a set-based F1-score of 34%on a test set of 135 ecologically-relevant queries and 775 candidate videos.In comparison the best zero-shot VLM achieved a F1-score of 18%, whilealso lacking interpretability.Project page: eceo-epfl.github.io/prompting-mammalps/

Understanding instructional videos requires recognizing fine-grained actions and modeling their temporal relations, which remainschallenging for current Video Foundation Models (VFMs). This diffi-culty stems from noisy web supervision and a pervasive “static bias”,where models rely on objects rather than motion cues. To address this,we propose InstrAct, a pretraining framework for instructional videos’action-centric representations. We first introduce a data-driven strategy,Project page: https://zyyangzy.github.io/InstrAct/which filters noisy captions and generates action-centric hard negativesto disentangle actions from objects during contrastive learning. At thevisual feature level, an Action Perceiver extracts motion-relevant tokensfrom redundant video encodings. Beyond contrastive learning, we intro-duce two auxiliary objectives: Dynamic Time Warping alignment (DTW-Align) for modeling sequential temporal structure, and Masked ActionModeling (MAM) for strengthening cross-modal grounding. Finally, weintroduce the InstrAct Bench to evaluate action-centric understanding,where our method consistently outperforms state-of-the-art VFMs onsemantic reasoning, procedural logic, and fine-grained retrieval tasks.

Models for image representation learning are typically de-signed for either recognition or generation. Various forms of contrastivelearning help models learn to convert images to embeddings that areuseful for classification, detection, and segmentation. On the other hand,models can be trained to reconstruct images with pixel-wise, perceptual,and adversarial losses in order to learn a latent space that is compati-ble with image generation. We seek to unify these two directions with afirst-of-its-kind model that learns representations which are simultane-ously well-suited for recognition and generation. We train our model asa hyper-network for implicit neural representation, which learns to mapimages to model weights for fast, accurate reconstruction. We furtherintegrate our INR hyper-network with knowledge distillation to improveits generalization and performance. Beyond the novel training design, themodel also learns an unprecedented compressed embedding space withoutstanding performance for various visual tasks. The complete modelcompetes with state-of-the-art results for image representation learning,enables downstream generative capabilities, and produces high-qualitytiny embeddings.

Intermediate representations are key to bridging the modal-ity gap between generalizable manipulation policies and large-scale pre-trained vision-language models (VLMs). Among these, trajectory-basedrepresentations compactly represent motion-relevant cues, yet most exist-ing approaches predict trajectories in 2D image space, resulting in intrin-sic 3D ambiguity. Moreover, using 2D trajectories with depth still leavesthe free-space waypoints ambiguous, limiting reliable 3D reasoning. Toaddress this, we propose predicting 3D consistent waypoints (3DWay)from multi-view images. By reformulating 3D waypoints prediction asgenerating multi-view consistent 2D waypoints followed by geometric tri-angulation, we enable explicit 3D motion specification while preservingthe strong priors of pretrained VLMs. The predicted waypoints can guideexisting VLA models for better generalization or be directly executed onsimple tasks. Extensive experiments show that 3DWay substantially im-proves 3D spatial grounding and vision-language reasoning, demonstrat-ing strong potential for generalizable robot manipulation. Codes will bereleased at https://github.com/ziqin-h/3DWay.

Medical image segmentation relies on the ability of encoder-decoderarchitectures to translate rich feature representations into accurate pixel-level pre-dictions under challenging conditions such as low contrast, structural ambigu-ity, and scale variability. While recent advances in large-scale pretraining andtransformer-based encoders have substantially improved feature extraction, seg-mentation accuracy remains constrained by decoder design, particularly in termsof cross-scale alignment, contextual integration, and boundary preservation. Inthis work, we revisit medical image segmentation from a decoder-centric per-spective and propose a context-aware gated decoder that systematically regulatesfeature fusion and contextual aggregation throughout the decoding process. Theproposed decoder integrates lightweight multi-scale channel recalibration, gatedskip fusion with spatial competition and a global context aggregation mechanismthat injects encoder-wide information into intermediate decoding stages. This de-sign enables effective translation of strong pretrained encoder representations intospatially consistent predictions. Extensive experiments across 11 medical imagesegmentation benchmarks validate the effectiveness and demonstrate that the pro-posed approach consistently outperforms strong baselines while remaining com-putationally practical. Code: https://github.com/saadwazir/MedCAGD

Existing Vision Foundation Model (VFM)-based iterativestereo pipelines under-exploit three information pathways: multi-scalebackbone features are collapsed into single-level correlations, geometricpriors remain untapped at initialization, and context propagates only lo-cally. These gaps widen under degraded photometric cues, making under-water scenes a stringent generalization test. To address this, we proposeLinStereo, built upon Depth Anything V3, whose core is a Position-Aware Linear Attention (PALA) module that replaces local recurrencewith global aggregation at linear cost, propagating reliable estimatesfrom well-matched regions into degraded areas while preserving dispar-ity structure. PALA is made effective by two enabling components: Hi-erarchical Semantic Cost Volumes (HSCV), which supply scale-alignedcorrelations from the VFM feature hierarchy, and a Depth Prior Ini-tialization (DPI) that converts monocular depth into a metrically cali-brated warm start. LinStereo achieves state-of-the-art-level accuracy onstandard benchmarks and strong cross-domain generalization, particu-larly on underwater scene where severe photometric degradation makesstereo matching particularly challenging, attaining the best overall ac-curacy with consistent gains (28% lower AbsRel on TartanAir-UW,26% on SQUID, a real-world underwater dataset). Code is availableat https://u7079256.github.io/LinStereo/.

Understanding animal motion is fundamental to modelinganimal behavior and biomechanics, yet progress in this area lags far be-hind human motion research due to the scarcity of high-quality motiondata. While human motion can be captured in controlled environments, itis impractical for most animal species, resulting in small, domain-limiteddatasets that restrict downstream applications such as animation. To ad-dress this challenge, we introduce Kirin, a framework that reconstructsmotion from video, learns motion priors at scale, and generates realisticmotion that can be directly applied to animated assets. Using large col-lections of in-the-wild animal videos, we reconstruct 3D motion sequencesand pair them with captions to create AiM3D, the first large-scale datasetoffering aligned video-text-motion tuples for quadruped animals. Build-ing on this dataset, we develop a visual-guided motion generation modelthat conditions on both text and image to guide the generation of re-alistic motion across diverse animal species. Finally, by leveraging anoff-the-shelf image-to-3D model, we automatically rig and animate 3Dmeshes using generated motion, producing ready-to-render animated an-imals. Together, our dataset and framework establish a new foundationfor large-scale, text and image conditioned animal motion generation andanimation. Project page: https://kirin-ani.github.io/.

Translating continuous, noisy egocentric video streams into discrete, temporally ordered action steps is fraught with visual challenges. Heavy ego-motion, transient occlusions, and the high intra-class variability of unscripted human-object interactions cause standard framelevel online temporal models to struggle, often resulting in severe oversegmentation and structural collapse. To bridge the gap between unstable low-level perception and high-level procedural logic, we present VidParse, a online, training-free framework that treats activity understanding as a graph-constrained inference problem. Rather than relying on learned temporal filters, we dynamically identify semantic transitions using a temporal similarity matrix over manipulation-anchored features, which are extracted from frozen foundation models to prioritize foreground hand-object interactions. A beam search decoder then leverages an induced procedural task graph to explicitly enforce valid action transitions and prune impossible trajectories. By anchoring robust visual segments to hard procedural constraints, our approach preserves longrange state transitions and achieves up to a 10x improvement in complex multi-step parsing accuracy over strong online baselines, all without requiring a single gradient update.

Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong domain priors. This keeps the field isolated from the broader Transformer ecosystem, limiting the transfer of research advances from other domains and the benefits of increasingly optimized software and hardware stacks. To bridge this gap, we propose the Volume Transformer (Volt), which adapts the vanilla Transformer encoder to 3D scenes with minimal modifications. Specifically, Volt partitions 3D scenes into volumetric patch tokens, processes them with full global self-attention, and injects positional information through 3D rotary positional embeddings (RoPE). Our initial experiments reveal that naively training Volt on standard 3D benchmarks leads to poor generalization, highlighting the limited scale of current 3D supervision. To overcome this, we introduce a data-efficient training recipe based on strong 3D augmentations, regularization, and distillation from a convolutional teacher, making Volt competitive with state-of-the-art methods. We then scale supervision through joint training on multiple datasets and show that Volt benefits more from increased scale than domain-specific 3D backbones, achieving state-of-the-art results across indoor and outdoor semantic segmentation benchmarks. Finally, we use Volt as a drop-in backbone in a standard 3D instance segmentation pipeline, where it also achieves new state-of-theart results, highlighting its potential as a simple, scalable, and generalpurpose backbone for 3D scene understanding.

Reliable localization of non-line-of-sight (NLOS) pedestriansis critical for safe urban autonomous driving, yet it remains highly chal-lenging in ego-dynamic outdoor environments, where ego-vehicle motionmakes radar multipath propagation complex and noisy. In this paper, wepresent a reflection-aware framework for NLOS pedestrian localizationwith a moving ego-vehicle in outdoor testbed scenarios. Our frameworkfuses front-view camera images and 2D radar point clouds to infer reflec-tion orders and reflective surface distributions in bird’s-eye-view space.It then uses physics-guided ray tracing to reconstruct distorted reflec-tion paths and localize the hidden pedestrian. We validate the frame-work in outdoor testbed scenarios under ego-dynamic conditions. The re-sults demonstrate the effectiveness of the proposed framework for NLOSpedestrian localization with a moving ego-vehicle.