ECCV 2026 论文列表

While high-quality preference data is vital for fine-grainedvision-language alignment, its creation remains bottlenecked by the highcost and subjective noise of human annotation. We propose a self-supervisedframework that derives solid, highly discriminative supervisory signalsthrough deterministic reconstruction feedback. By transforming abstractsemantic matching into concrete visual reconstruction, our approach pro-vides reliable consistency signals that overcome the input limits of tra-ditional models. A reward model trained on our generated data achievescompetitive accuracy across multiple zero-shot preference benchmarksusing only 20% of the typical training data volume. Furthermore, fine-tuning VLMs via Direct Preference Optimization (DPO) based on thisdata significantly improves performance in handling complex, high-densitydescriptions. Our results demonstrate the potential of reconstruction-driven self-correction for low-cost, high-precision alignment of multi-modal models. Our code of the scoring model is released at https://github.com/XC0053/iterative-perceptual-alignment.

Vision-Language Models (VLMs) have demonstrated remark-able success across diverse visual tasks, yet their performance degradesin complex visual environments. Existing enhancement approaches re-quire additional training, rely on external segmentation tools, or operateat coarse-grained levels, overlooking VLMs’ innate attention capabilities.To bridge this gap, we investigate VLMs’ attention patterns and discoverthat: (1) visual complexity strongly correlates with attention entropy,negatively impacting reasoning performance; (2) attention progressivelyrefines from global scanning in shallow layers to focused convergencein deeper layers, with the degree of convergence determined by visualcomplexity; (3) theoretically, under a multiplicative decomposition as-sumption, we show that contrasting attention maps between general andtask-specific queries approximately separates visual signal into seman-tic and visual noise components. Building on these insights, we proposeContrastive Attention Refinement for Visual Enhancement (CARVE),a training-free method that extracts task-relevant visual signals throughattention contrasting at the pixel level. Experiments on seven bench-marks show that CARVE improves performance on visual perceptiontasks, with notable gains on both recent and earlier-generation models.Our analysis reveals how visual complexity affects attention mechanismsand demonstrates an effective strategy for improving visual reasoningthrough attention contrasting.

Diffusion prior-based methods have shown impressive resultsin real-world image super-resolution (ISR), yet two key challenges per-sist: balancing pixel-level fidelity with semantic quality, and adapting todiverse degradations. Existing dual-branch approaches freeze the pixelmodule during semantic training, but the semantic branch can still ex-pand capacity within the pixel subspace, precluding genuine perceptualimprovement. Moreover, using a single static adapter cannot generalizeacross heterogeneous real-world corruptions. To address both issues, wepropose FreqOrtho-SR, which comprises: Frequency-guided Mixture ofLoRA Experts (FreqMoE), it routes inputs to specialized experts via anon-parametric FFT-based degradation-feature extractor that encodesfrequency-domain signatures, enabling stable and interpretable special-ization across corruption types; and Orthogonal Gradient Projection(OGP), which reframes the dual-objective optimization as a subspace-constrained problem: by extracting the pixel-fidelity subspace via SVDon combined expert weight deltas and projecting semantic gradients ontoits null space, OGP guarantees orthogonality between the two objectives,enabling genuinely complementary learning without mutual interference.Experiments show that FreqOrtho-SR achieves competitive overall per-formance and a strong fidelity-perception trade-off across multiple bench-marks with efficient single-step inference. The source code of our methodcan be found at sonhm3029/FreqOrtho-SR.

Few-shot Test-Time Domain Adaptation (FSTT-DA) seeksto adapt models to novel domains using only a handful of unlabeledtarget samples. This setting is more realistic than typical domain adap-tation setups, which assume access to target data during source training.However, prior FSTT-DA approaches fail to effectively leverage sourcedomain-specific knowledge, relying on shallow batch normalization up-dates, prompt-based methods that treat the model as a black box, orensembling strategies that do not capture cross-domain relationships. Toaddress these limitations, we introduce a new FSTT-DA framework thatintegrates LoRA fine-tuning with model merging. In our approach, sep-arate LoRA modules are fine-tuned on CLIP’s vision encoder for eachsource domain. Since LoRA modifies only a small fraction of the model’sparameters, it retains the base model’s generalized knowledge while in-ternally learning domain-specific features. To adapt the learned knowl-edge to a specific target domain, we propose a hypernetwork trainedvia meta-learning that generates per-column merging factors to combineLoRA modules. Given a small batch of target images, the hypernetworkproduces merging weights that fuse source LoRA modules into a singleadapted representation. Our results demonstrate state-of-the-art perfor-mance across various domain adaptation datasets. Our code is publiclyavailable at https://github.com/nahbois4321/DA-MergeLoRA.

Automated chest X-ray report generation has recently bene-fited from reinforcement learning (RL) and large language models. How-ever, RL training often suffers from instability or limited explorationdue to fixed Kullback-Leibler (KL) regularization and a static referencepolicy that accumulates KL pressure over time. We propose Response-Weighted and Validation-Anchored Policy Optimization (REVA-PO), aRL framework that stabilizes long-term training via Response-WeightedRegularization (RER) and Validation-Anchored Policy Reset (VAPR).RER dynamically adjusts per-response KL weights based on advantageand reference-policy entropy, relaxing constraints for high-quality re-sponses while tightening them for low-quality ones. Complementarily,VAPR periodically synchronizes the reference and current policies tothe best validation checkpoint, resetting accumulated regularization pres-sure to expand the viable exploration space. To ensure a robust startingpoint, we employ a three-stage pipeline consisting of warm-up training,classifier-guided supervised fine-tuning, and RL. Extensive evaluationson MIMIC-CXR and IU-Xray demonstrate that REVA-PO sets newstate-of-the-art benchmarks in both linguistic quality and clinical accu-racy. Notably, BLEU-4 improves by 5.1% on MIMIC-CXR and 3.6% onIU-Xray, while CheXpert F1 and RadGraph F1 scores increase by 4.5%and 12.8%, respectively, over prior leading methods. The code is publiclyavailable at https://github.com/LiGuo12/REVA_PO/.

We present UniQueR, a unified query-based feedforward framework for efficient and accurate 3D reconstruction from unposed images. Existing feedforward models such as DUSt3R, VGGT, and AnySplat typically predict per-pixel point maps or pixel-aligned Gaussians, which remain fundamentally 2.5D and limited to visible surfaces. In contrast, UniQueR formulates reconstruction as a sparse 3D query inference problem. Our model learns a compact set of 3D anchor points that act as explicit geometric queries, enabling the network to infer scene structure— including geometry in occluded regions—in a single forward pass. Each query encodes spatial and appearance priors directly in global 3D space (instead of per-frame camera space) and spawns a set of 3D Gaussians for differentiable rendering. By leveraging unified query interactions across multi-view features and a decoupled cross-attention design, UniQueR achieves strong geometric expressiveness while substantially reducing memory and computational cost. Experiments on Mip-NeRF 360 and VR-NeRF demonstrate that UniQueR surpasses recent feedforward baselines in both rendering quality and geometric accuracy, using an order of magnitude fewer primitives than dense alternatives.

We present Spectral Consistent Flow (SC-Flow), a 3D med-ical image translation framework with a single function evaluation (1-NFE) in the latent space. This approach reformulates medical imagetranslation as a stochastic Brownian bridge process that directly con-structs a mapping between source and target modalities by predictingthe support regularized mean velocity field. To mitigate modality entan-glement, over-smoothing, and artifacts induced by the implicit low-passmodulation of the latent average velocity, we introduce a Spectral Consis-tency Corrector that dynamically regularizes the evolution of the powerspectral density via learnable frequency-domain gain modulation. Thismechanism establishes an explicit bridge between spatial textures andspectral energy flow, enabling the model to recover fine-grained anatom-ical fidelity while maintaining global structural coherence. Extensive ex-periments on four datasets demonstrate that SC-Flow delivers signifi-cantly more accurate, consistent, and robust performance across varioustranslation scenarios.

Personalized image retouching aims to adapt retouching stylesof individual users from reference examples, but existing methods oftenrequire user-specific fine-tuning or fail to generalize effectively. To addressthese challenges, we introduce RefRetouch, a general framework forpersonalized image retouching that instantly adapts to user retouchingstyles without any test-time fine-tuning. It employs an asymmetric auto-encoder to encode the retouching style from paired examples into a con-tent disentangled latent representation that enables faithful transfer ofthe retouching style to new images. To adaptively apply the encoded re-touching style to new images, we further propose retrieval-augmented re-touching (RAR), which retrieves and aggregates style latents from refer-ence pairs most similar in content to the query image. With these compo-nents, RefRetouch enables superior and generic content-aware retouch-ing personalization across diverse scenarios, including single-reference,multi-reference, and mixed-style settings, while also generalizing out ofthe box to photorealistic style transfer.

Spin plays a crucial role in many ball sports due to its effecton the trajectory of the ball. Vision-based estimation of the ball’s spinduring a game with conventional cameras is challenging due to the ball’ssmall size, high speed, and fast rotation. To address these challenges, wepropose an event-based active vision system that can track unmodifiedballs and measure their spin in real time. The system consists of an eventcamera for its high temporal resolution and minimal motion blur, high-speed pan/tilt galvanometer mirrors to keep the ball in the field of view,and a low-latency focus-tunable telephoto lens to increase the spatial res-olution on the ball and keep it in focus. To track the ball, we use a hybridapproach that combines 2D event-based detection for centering and 3Dpositions from a ball localization system for re-initialization. For high-accuracy spin estimation, we propose an offline method that performscontrast maximization on the sphere (s-CMax). This method achievesstate-of-the-art accuracy on static balls across multiple sports (table ten-nis, baseball, tennis, and golf), with mean magnitude and axis errors of1.2% and 1.5 degrees, respectively. We then develop a low-latency onlinemethod for table tennis as a case study in real-time applications. Thismethod uses an uncertainty-aware convolutional neural network trainedon pseudo-ground-truth spin labels from the offline approach, combinedwith a GPU-accelerated batch implementation of contrast maximizationfor refinement. We demonstrate reliable tracking and spin estimationwith a three-view setup during professional table tennis matches, withhigh accuracy (8.8% magnitude and 6.4 degrees axis mismatch w.r.t. theoffline method), 3 ms latency, and 750 Hz throughput.

Long-term aerial localization requires matching live flightimagery against archival reference maps, demanding feature represen-tations that are invariant to severe appearance changes and perceptualaliasing. However, current benchmarks report only aggregate accuracyover predominantly man-made environments, masking severe terrain-dependent performance gaps. As a result, localization performance overunstructured natural landscapes—where self-similar textures and drasticseasonal changes dominate—remains effectively unmeasured. To addressthis, we introduce Leaving the City, the first large-scale aerial benchmarkdesigned to isolate and quantify terrain-dependent localization gaps. Cap-tured via a microlight aircraft, our dataset comprises 1,379 km of flighttrajectories flown repeatedly to capture distinct seasonal variations. Wepair high-frame-rate imagery and inertial measurements with semanticterrain masks, multi-year-old orthophotos, and precise 6-DoF groundtruth. Evaluating state-of-the-art matchers through our terrain-stratifiedprotocol reveals a systematic bias: methods that succeed on man-madesurfaces degrade sharply over natural terrain undergoing strong appear-ance change. By exposing where current methods fail, our benchmarkprovides a rigorous foundation for developing robust, all-terrain aeriallocalization. The dataset and code are publicly available.4

Accurate anatomical structure segmentation in medical im-age is essential for diagnosis and treatment planning. While recent inter-active segmentation foundation models enhance generalization throughlarge-scale multimodal pretraining, they still depend on precise promptsand can fail in underrepresented clinical contexts (e.g., small organs-at-risk). We present AtlasSegFM, an atlas-guided framework that cus-tomizes off-the-shelf foundation models to new clinical contexts with asingle annotated example. AtlasSegFM 1) performs atlas-query regis-tration to generate context-aware prompts, 2) refines the segmentationwith a frozen foundation model, and 3) applies a lightweight adaptivefusion module to combine atlas priors with foundation-model inputs andpredictions. Extensive experiments on six public and in-house datasetsacross radiotherapy and vascular scenarios show consistent gains, withthe largest improvements on small and delicate structures. AtlasSegFMprovides a lightweight, deployable solution for one-shot customization ofsegmentation foundation models in real-world clinical workflows.

Masked autoencoding has emerged as a prominent paradigmfor self-supervised learning on 3D point clouds, achieving competitiveperformance across downstream tasks. Unlike its 2D counterpart, 3Dmasked autoencoding directly reconstructs spatial coordinates, makingit inherently susceptible to positional leakage. In this work, we identifythat the decoder in existing 3D MAE frameworks tends to over-rely onpositional information, which weakens semantic representation learningand leads to suboptimal feature quality. To address this issue, we proposeMPL-MAE, a masked point learning framework that mitigates positionalover-reliance while enhancing the utilization of encoder features. Specifi-cally, we introduce a recalibrated positional embedding module that sup-presses metric-dominant coordinate signals while preserving geometrictopology, together with a gated positional interface module that dynam-ically regulates positional injection during reconstruction. These designspromote a more balanced interaction between spatial priors and seman-tic features, yielding robust and informative representations. Extensiveexperiments across downstream tasks demonstrate that MPL-MAE con-sistently achieves competitive performance, validating its effectiveness.Code is available at https://github.com/yanx57/MPL-MAE.

Standard pipelines for physics-ready 3D reconstruction relyon a decoupled two-stage paradigm: extracting surface geometry followedby an error-prone tetrahedralization process. While recent Lagrangianmethods like TetSphere Splatting attempt to bypass this by directlyoptimizing volumetric primitives, their homeomorphic constraints pre-vent topology-adaptive optimization. Consequently, they produce dis-joint tetrahedra rather than a single connected mesh, rendering thestructures unsuitable for further physical simulations. To address this,we propose a topology-adaptive framework for holistic tetrahedral meshreconstruction through end-to-end topological and geometric optimiza-tion. First, by coupling Gaussian spheres to tetrahedral elements andleveraging edge connections, we estimate a continuous opacity field fordifferentiable element pruning. Next, jointly minimizing mesh smoothingenergy and multi-view Gaussian rendering error drives alternating geo-metric refinement while preserving topological adaptivity. Consequently,our approach effectively constructs a unified and topologically coherenttetrahedral mesh. Extensive experiments demonstrate that our methodoutperforms state-of-the-art techniques by achieving superior geometricaccuracy and producing coherent, single-connected tetrahedral meshes,thereby effectively bypassing the error-prone conventional tetrahedraliza-tion step for reconstructed surface meshes and streamlining downstreamphysical simulation.

Multi-objective masked image modeling (MIM) combines com-plementary learning signals (token distillation, CLS alignment, and pixelreconstruction) but existing methods weight these objectives with globalscalars, ignoring spatial heterogeneity across patches. We present Ex-PLoRe (Expert Patch-Level Loss Routing), which repurposes Soft Mix-ture of Experts (MoE) dispatch weights as learned, per-patch loss coef-ficients. The key mechanism is loss-coupling: allowing loss gradients toflow through dispatch weights to the router enables content-dependentspecialization, where different patches receive different emphases acrossobjectives. A detach ablation confirms loss-coupling as the core mecha-nism, degrading performance by 1.6% when gradients are blocked. OnImageNet-1K with ViT-Base, ExPLoRe improves over non-MoE base-lines on two objective combinations (Token+CLS: +0.5% k-NN, +4.4%linear probe; Token+Pixel: +2.2% k-NN), achieving 80.6% linear probeand 85.3% finetuning accuracy, competitive with published methods. Fordownstream transfer, we develop adaptation recipes (Freeze Routing, Ex-pert Dropout, and Freeze Attention) that improve MoE finetuning by+1.5% over the vanilla MoE, and close a 2.5–2.9 mIoU segmentation gapso that MoE models match or exceed non-MoE baselines on ADE20K.

Recent generative approaches to geometry estimation adaptpretrained image diffusion models and treat the task as image-conditionedgeneration. Leveraging off-the-shelf image diffusion models, they either(i) train task-specific geometry models (for depth and surface normal es-timation) independently, losing the opportunity of exploring the intrinsiccorrelation of these geometric targets, or (ii) jointly fine-tune modifiedimage diffusion backbones (e.g., altered self-attention), which typicallydemands substantial labeled data. To overcome these limitations in aprincipled fashion, we repurpose pretrained video generative models as aunified and data-efficient framework for geometry estimation, formulatedinnovatively as a next-frames prediction task. Our method, GeoNeXt,inherits naturally structured knowledge and richer priors from the videomodel, while further adapting them for joint modeling of images and ge-ometry targets (

Towards an embodied generalist for real-world interaction,Multimodal Large Language Model (MLLM) agents still suffer fromchallenging latency, sparse feedback, and irreversible mistakes. Videogames offer an ideal testbed with rich visual observations and closed-loopinteraction, demanding fine-grained perception, long-horizon planning,and precise control. However, systematically evaluating these capabilitiesis currently hindered by heterogeneous action interfaces and heuristicverification. To this end, we introduce GameWorld, a benchmarkdesigned for standardized and verifiable evaluation of MLLMs as generalistgame agents in browser environments. Two game agent interfaces arestudied: (i) Computer-use agents that directly emit keyboard and mousecontrols, and (ii) Generalist multimodal agents that act in a semanticaction space via deterministic Semantic Action Parsing. GameWorldcontains 34 diverse games and 170 tasks, each paired with state-verifiable metrics for outcome-based evaluation. The results across 18model-interface pairs suggest that even the best-performing agent isfar from achieving human capabilities on video games. Further studieson real-time interaction, context-memory sensitivity, and action validityexpose more challenges ahead for game agents. Together, by offering astandardized and verifiable evaluation framework, GameWorld laysa foundation for advancing research on multimodal game agents andbeyond.

Pixel-aligned Gaussian splatting enables efficient and gen-eralizable novel-view synthesis. However, high-resolution rendering facesa critical trade-off where increasing input resolution improves detail atthe expense of quadratically rising network computational cost. Con-versely, maintaining low-resolution inputs stabilizes this cost but resultsin insufficient Gaussian density and artifacts. To address this, we proposeSubSplat, which introduces Sub-pixel Gaussian Reparameterizer(SPGR)to subdivide primary Gaussians into fine-grained primitives, restoringstructural density directly from low-resolution features. We further en-hance the reparameterization quality through feature aggregation, whicheffectively captures high-frequency details across multiple views. Experi-ments on RealEstate10K and ACID demonstrate that SubSplat achieveshigh-fidelity rendering with superior efficiency. Our results validate thatthe proposed framework successfully resolves the trade-off between repa-rameterization fidelity and network computational cost inherent in pixel-aligned Gaussian Splatting.

Cross-view geo-registration is the task of aligning a queryimage to a geodetically accurate reference (e.g., satellite image), so thateach query pixel maps to a real-world GPS coordinate. Most existingwork addresses the related problem of cross-view geo-localization, wherethe goal is typically to estimate the camera center using retrieval, classi-fication, matching, or regression. Because these approaches do not pro-vide dense supervision, they are poorly suited for learning and eval-uating pixel-wise alignment. We introduce SkyReg, a geometry-awaregeo-registration model that estimates the transformation between thequery and reference images by explicitly modeling the 3D scene ge-ometry. Applying this transformation to warp the query into the ref-erence frame yields pixel-wise geo-localization, without relying on 2Dpoint matches, and remains robust to occlusions and large viewpointchanges. To enable training and standardized evaluation, we release (i)SkyReg-Train, a large-scale dataset of drone–satellite images annotatedwith per-pixel GPS coordinates, depth maps, and camera parameters de-rived from LiDAR and structure-from-motion, and (ii) SkyReg-Bench, aheld-out benchmark of unseen Urban and Suburban scenes with the samedense annotations. SkyReg achieves state-of-the-art performance againststrong retrieval and homography baselines, demonstrating the value ofgeometry-aware models and dense geodetic benchmarks for cross-viewgeo-registration. Dataset available at https://parthpk.github.io/skyreg-webpage.

Medical image modality translation is hindered by the entan-glement of geometry and modality-specific textures, often causing struc-tural distortions. Existing methods operate at the pixel or feature level,failing to separate geometry from appearance and yielding anatomicallyinconsistent results. We present Proto-Gaussian, a novel MRI modalitytranslation framework that explicitly disentangles structural geometryfrom modality-specific appearance using 2D Gaussian image representa-tion, surpassing conventional pixel or patch-based approaches in preserv-ing anatomical consistency. The framework operates in two stages: first, ashared Gaussian Bank captures modality-invariant geometric prototypesthrough 2D Gaussian primitives and self-supervised learning; second, aLabel-Adaptive Token Refinement module maps texture features acrossmodalities while leveraging the learned geometric structures, achievingclear structure-texture separation. Finally, a fully differentiable 2D Gaus-sian splatting renderer synthesizes high-fidelity target-modality images,maintaining both structural accuracy and visual realism. Extensive ex-periments on brain MRI datasets demonstrate the superiority of ourmethod through quantitative and qualitative comparisons with state-of-the-art approaches.