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.

ECCV 2026

Incentivizing Vision Language Models to Search for Long Video Question Answering

Harsh Goel, S P Sharan, Sahil Shah, Minkyu Choi, Joungbin An, Kristen Grauman, Sandeep Chinchali

We introduce VSeek, an agentic framework that transformslong-video question answering (LVQA) from a passive, single-pass per-ception task into a multi-turn retrieval process. VSeek utilizes a naturallanguage-driven search to identify relevant context within long videosand is post-trained with reinforcement learning (RL) to jointly formulatetargeted search queries and reason over retrieved clips for LVQA. WhileRL post-training has revolutionized reasoning in symbolic domains suchas mathematics and code, its application to long-video understandingremains hindered by a lack of verified rewards. To ensure that the re-trieved context is relevant, we propose a novel neuro-symbolic approachthat bridges open-ended natural language with discrete visual verifica-tion. Specifically, complex user queries are compiled into formal tempo-ral logic specifications for systematically decomposing natural languagequestions into a definitive checklist of required atomic visual primitives,such as key objects and activities, along with their temporal ordering.These systematically derived grounding events provide the critical feed-back signal for RL post-training, enabling dense, verifiable rewards basedon the successful retrieval of these specific visual elements rather thanrelying entirely on outcome-only answer accuracy. By explicitly optimiz-ing for this verifiable evidence-seeking behavior, VSeek improves Pass@1scores by up to 8% and Pass@4 scores by 15% on long-video understand-ing benchmarks compared to base models. We open-source our code athttps://utaustin-swarmlab.github.io/VSeek.

ECCV 2026

Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation

Chonghuinan Wang, Zhikai Chen, Chunwei Wang, Yecong Wan, Junwei Yang, Zhixin Wang, Wei Zhang, Jiaqi Xu, Renjing Pei, Xiaohe Wu, Fan Li, Wangmeng Zuo

The advancement of generative AI models capable of pro-ducing text and image marks a critical step forward in the realm of* Equal Contribution, B Corresponding Author, † Project Leadermultimodal intelligence, particularly for tasks involving the interleavingof both modalities. To advance this intelligence to the next stage, it iscrucial for models to autonomously generate free-form interleaved text-image sequences. In this paper, we introduce ILLUME-X, an advancedunified multimodal paradigm that enables high-quality, free-form inter-leaved text-image generation by improving multimodal data efficiencyand stabilizing the multimodal training process. ILLUME-X comprisesthree key components: (i) an expanded training data pipeline optimizedfor interleaved text-image generation, (ii) a progressive training strategywith self-adaptive objectives for free-length multimodal token sequences,and (iii) an objective and comprehensive evaluation method ILScore forinterleaved text-image sequences. Notably, our ILLUME-X outperformsprevious unified models across multiple interleaved text-image generationtasks like style transfer, image decomposition and storytelling.

ECCV 2026

HolisticSemGes: Semantic Grounding of Holistic Co-Speech Gesture Generation with Contrastive Flow-Matching

Lanmiao Liu, Esam Ghaleb, Asli Ozyurek, Zerrin Yumak

While the field of co-speech gesture generation has seen sig-nificant advances, producing holistic, semantically grounded gestures re-mains a challenge. Existing approaches rely on external semantic re-trieval methods, which limit their generalisation capability due to de-pendency on predefined linguistic rules. Flow-matching-based methodsproduce promising results; however, the network is optimised usingonly semantically congruent samples without exposure to negative ex-amples, leading to learning rhythmic gestures rather than sparse mo-tion, such as iconic and metaphoric gestures. Furthermore, by modellingbody parts in isolation, the majority of methods fail to maintain cross-modal consistency. We introduce a Contrastive Flow Matching-basedco-speech gesture generation model that uses mismatched audio–textconditions as negatives, training the velocity field to follow the cor-rect motion trajectory while repelling semantically incongruent trajec-tories. Our model ensures cross-modal coherence by embedding text,audio, and holistic motion into a composite latent space via cosine andcontrastive objectives. Extensive experiments and a user study demon-strate that our proposed approach outperforms state-of-the-art methodson two datasets, BEAT2 and SHOW. Our project page is available at:https://marcos452.github.io/HoliticSemGes/

ECCV 2026

GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models

Bozhou Li, Sihan Yang, Yushuo Guan, Ruichuan An, Xinlong Chen, Yang Shi, Pengfei Wan, Wentao Zhang, Yuanxing Zhang

The text encoder is a critical component of text-to-image andtext-to-video diffusion models, fundamentally determining the semanticfidelity of the generated content. However, its development has been hin-dered by two major challenges: the lack of an efficient evaluation frame-work that reliably predicts downstream generation performance, and thedifficulty of effectively adapting pretrained language models for visualsynthesis. To address these issues, we introduce GRAN-TED, a paradigmto Generate Robust, Aligned, and Nuanced Text Embeddings for Diffu-sion models. Our contribution is twofold. First, we propose TED-6K, anovel text-only benchmark that enables efficient and robust assessmentof an encoder’s representational quality without requiring costly end-to-end model training. We demonstrate that performance on TED-6K,standardized via a lightweight, unified adapter, strongly correlates withan encoder’s effectiveness in downstream generation tasks. Notably, un-der our experimental setup, compared with training a diffusion modelfrom scratch, evaluating with TED-6K is about 750× faster. Second,guided by this validated framework, we develop a superior text encoderusing a novel two-stage training paradigm. This process involves an ini-tial fine-tuning stage on a Multimodal Large Language Model for bettervisual representation, followed by a layer-wise weighting method to ex-tract more nuanced and potent text features. Our experiments show thatthe resulting GRAN-TED encoder not only achieves state-of-the-art per-formance on TED-6K but also leads to demonstrable performance gainsin text-to-image and text-to-video generation.

ECCV 2026

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

Mingxin Liu, Ziqian Fan, Zhaokai Wang, Leyao Gu, Zirun Zhu, YiguoHe YiguoHe, Yuchen Yang, Changyao Tian, Xiangyu Zhao, Ning Liao, Shaofeng Zhang, Qibing Ren, Zhihang Zhong, Xuanhe Zhou, Junchi Yan, Xue Yang

Unified multimodal models target joint understanding, rea-soning, and generation, but current image editing benchmarks are largelyconfined to natural images and shallow commonsense reasoning, offeringlimited assessment of this capability under structured, domain-specificconstraints. In this work, we introduce GRADE, the first benchmarkto assess discipline-informed knowledge and reasoning in image editing.GRADE comprises 520 carefully curated samples across 10 academicdomains, spanning from natural science to social science. To supportrigorous evaluation, we propose a multi-dimensional evaluation proto-col that jointly assesses Discipline Reasoning, Visual Consistency, andLogical Readability. Extensive experiments on 20 state-of-the-art open-source and closed-source models reveal substantial limitations in currentmodels under implicit, knowledge-intensive editing settings, leading tolarge performance gaps. Beyond quantitative scores, we conduct rigor-ous analyses and ablations to expose model shortcomings and identifythe constraints within disciplinary editing. Together, GRADE pinpointskey directions for the future development of unified multimodal models,advancing the research on discipline-informed image editing and reason-ing. Our benchmark and evaluation code are publicly released.

ECCV 2026

From Script to Shot: A Benchmark for Grounding Screenplays in Movies

Jungu Cho, Young-Jae Park, Seong Jong Ha, Siyeol Kim, Seungho Park, Jisu Shin, Junmyeong Lee, Chaemin Hwang, Hyunjun Jung, Sangeyl Lee, Hae-Gon Jeon

Aligning screenplay scenes to video shots is a foundationaltask for narrative video understanding. Unlike subtitles or captions,screenplays combine dialogue, visual direction, and narrative cues in asingle document, making them ill-suited for standard video-text retrievaland leaving prior methods to exploit only subtitle overlaps. Methodsranging from alignment based on textual subtitle to contrastive encodersand temporal grounding networks can potentially bridge this gap, yetno benchmark systematically compares these paradigms or isolates thecontributions of dialogue and visual information to alignment quality.We introduce “From Script to Shot”, a benchmark of 50 feature filmsspanning nine decades with over 55K shot-level scene alignment an-notations verified by human annotators. To disentangle text matchingfrom visual grounding, we evaluate fourteen approaches—from sparsetext retrieval to recent vision-language models such as FG-CLIP 2 andQwen3-VL-Embedding, on an identical pipeline. Dialogue-based retrievalperforms poorly on non-dialogue scenes, and contrastive encoders aloneunderperform direct text matching. Adaptive multimodal fusion achievesthe strongest overall results, reaching 0.599 mSIoU when BM25 is fusedwith a Qwen3-VL-Embedding, yet even the strongest encoder leaves aconsistent gap between dialogue and non-dialogue scenes, exposing thelimits of current visual encoding for narrative grounding. By quantify-ing this gap, the benchmark provides a controlled testbed for studyingscreenplay-conditioned alignment. We demonstrate downstream utilitythrough zero-shot movie scene segmentation and screenplay-guided videogeneration, confirming that the alignment signal generalizes beyond thebenchmark itself. We release the full dataset, parser and parser outputs,toolkit, and baselines at https://github.com/jungucho92/script2shotto support research on long-form multimodal video understanding.2 J. Cho et al. 사용 폰트: 노토산스한국:https://fonts.google.com/noto/specimen/Noto+Sans+KRScreenplay -Video Alignment Prior works(dialogue -based)Screenplay SCENE 69 dialogue D D D D D Dthe script of a movie,H INT HOTEL ROOM-HOURS LATERincluding actinginstructions and D HAZEL Good morning.subtitle#69 scene directions. D FRANNIE Actually, it'sfive o'clock.Good morning. … it's five o’ … How was the park? Good morning. … it's five o’ … How was the park?D HAZEL How was the park? D D D D D D. D FRANNIE Never made it.D HAZEL Mom, what do you mean? Never made it. Mom, what … … do you mean? Never made it. Mom, what … … do you mean?#70 H headingSCENE 70 mixedfectly tailored BLACK H INT HOTEL ROOM– LATERN D D D D DN Frannie opens the door to find GusGus is here. (TO GUS) in a perfectly tailored BLACK SUIT.partial Looking sharp. Thank you ma’am . Looking sharp. Thank you ma’am . Hazel! Gus is here.D FRANNIE Hazel! Gus is here. (TOD dialogue GUS) Looking sharp.D N D N Dbathroom. She wears a D GUS Thank you ma’am.Not predictedhe looks... N A few beats later, Hazel appears in aHazel! Gus is here. Wow. Wow.pale blue sundress.D GUS Wow.N narrativeSCENE 86 non-dialogueey're readyE CLAIM to go.– DAY no subtitle ✘ N N NShot 1465 H INT AIRPORT– DAYs Michael standing Not predicted Not predicted Not predictedN Michael with sign: “My Beautiful Family.”that says - instead of #86 He kisses his wife, and hugs Hazel.y (and Gus)." Uponcourse. He kisses his Notation SCREENPLAY VIDEO SHOTS (KEYFRAMES)ake his hand butFig. 1: Screenplay-video alignment maps each shot to its corresponding screenplayscene. Each scene combines a scene heading (H), narrative direction (N), and dialogue(D). Shots carry subtitle text only when spoken dialogue is present. Prior dialogue-based methods align subtitle-matched shots correctly but fail entirely on non-dialoguescenes, whereas our benchmark evaluates all scene types under a unified protocol.

ECCV 2026

FlowLess: Controlling Abstract Image Generation

Amir Hertz, Noah Snavely

Reinforcement learning (RL) has become a standard tech-nique for post-training diffusion-based image synthesis models, as itenables learning from reward signals to explicitly improve desirable as-pects such as image quality and prompt alignment. In this paper, wepropose an online RL variant that reduces the variance in the modelupdates by sampling paired trajectories and pulling the flow velocityin the direction of the more favorable image. Unlike existing methodsthat treat each sampling step as a separate policy action, we considerthe entire sampling process as a single action. We experiment with bothhigh-quality vision language models and off-the-shelf quality metrics forrewards, and evaluate the outputs using a broad set of metrics. Ourmethod converges faster and yields higher output quality and promptalignment than previous approaches.

ECCV 2026

FlashBEV: Fast and Memory-Efficient Exact BEV Transformation with IO-Awareness

Shunsuke Yokokawa, Hironori Kasahara

Bird’s-eye-view (BEV) perception is a core component of camera-based 3D understanding in autonomous driving, where view transformation (VT) maps multi-camera image features into a uni(cid:28)ed BEV representation. Sampling-based view transformation (Sampling-VT) is attractive because it supports dense and continuous BEV aggregation for high-resolution and long-range perception. Its deployment bottleneck, however, is systems-level: standard tensorized implementations of Sampling-VT(cid:22)which we refer to as Tensorized Sampling-VT(cid:22)explicitly materialize large height-dependent intermediate tensors, causing memory and latency costs that scale poorly with vertical resolution and the number of cameras. We revisit Tensorized Sampling-VT from an operator-execution perspective and show that it follows a gather(cid:21)reduction pattern: each BEV query independently accumulates contributions across cameras and height bins. Unlike splatting-based VT, which requires index sorting and prevents fully thread-local reduction from voxel construction to BEV output, the gather(cid:21)reduction structure of Sampling-VT enables thread-local accumulation with on-the-(cid:29)y recomputation, eliminating the need to materialize heightand camera-dependent intermediates. Based on this insight, we propose FlashBEV, a fully fused and IOaware execution strategy that is mathematically equivalent to Tensorized Sampling-VT (same operator output) while substantially reducing global memory tra(cid:30)c and kernel-launch overhead. Experiments show that FlashBEV achieves more than an order of magnitude lower peak GPU memory and signi(cid:28)cant inference-latency speedups, with memory usage effectively independent of the number of height bins, reducing the operator’s peak memory to O(BCXY ) (output only). This unlocks higher BEV range/resolution and vertical discretization within (cid:28)xed deployment budgets on memory-constrained devices, where tensorized execution would otherwise be infeasible. Our contribution is therefore an execution redesign(cid:22)same math, di(cid:27)erent execution(cid:22)that removes a key scalability barrier for deployment-ready Sampling-VT. Code is available at https://github.com/yokosyun/FlashBEV. • •

ECCV 2026

FingerCap: Fine-grained Finger-level Hand Motion Captioning

Xin Shen, Rui Zhu, Lei Shen, Zhuojie Wu, Xinyu Wang, Kaihao Zhang, Tianqing Zhu, Shuchen Wu, Chenxi Miao, Weikang Li, Deguo Xia, Jizhou Huang, Xin Yu

Understanding human hand motion requires reasoning thatgoes beyond coarse action semantics to capture detailed finger articula-tion and interaction dynamics. However, existing Video-MLLMs primar-ily capture global action intent and often fail to represent fine-grainedfinger-level movements and contact semantics. In this work, we proposeFine-grained Finger-level Hand Motion Captioning (FingerCap), whichaims to generate textual descriptions that capture detailed finger-levelsemantics of hand actions. To support this task, we curate FingerCap-40K, a large-scale corpus of 40K paired hand-motion videos and captionsspanning two complementary sources: concise instruction-style finger mo-tions and diverse, naturalistic hand–object interactions. Furthermore,we design HandJudge, an LLM-based rubric that measures finger-level correctness and motion completeness for effective evaluation. Toestablish a strong yet lightweight baseline under the FingerCap task,we introduce FiGOP (Finger Group-of-Pictures), a module tailoredfor Video-MLLM settings with sparse RGB sampling. FiGOP augmentskeyframes with intermediate 2D hand keypoints, enabling complemen-tary motion cues without increasing the density of RGB frames. Exper-iments on FingerCap-40K show that strong open- and closed-sourceVideo-MLLMs still struggle with finger-level reasoning, while our FiGOP-enhanced model yields consistent gains under both HandJudge and hu-man studies. The dataset and benchmark are available at § FingerCap.

ECCV 2026

FaceArmor: A Universal Facial Image Protection Against Diffusion-Based Manipulations

Yiming Wang, Jiahao Chen, Qingming Li, Chunyi Zhou, Zhi Chen, Lingzhong Meng, Jinbao Li, Shouling Ji

The rapid advancement of diffusion models has exacerbatedprivacy risks by enabling realistic manipulations of personal facial im-ages. Existing proactive defenses primarily target model-specific internalmodules under restrictive white-box assumptions, rendering their pro-tective efficacy highly vulnerable to unseen architectures and manipula-tion paradigms. To bridge this gap, we propose FaceArmor, a universalfacial image protection framework against both unknown generative ar-chitectures and real-world environmental transformations. Unlike priormodel-dependent approaches, FaceArmor focuses on the intrinsic fea-ture composition of facial images. It leverages an ensemble of surrogateextractors to decompose representations into a structural tier targetinglatent reconstruction and fine textures, and a semantic tier obscuringprompt alignment and biometric identities. These complementary di-mensions are universally exploited by mainstream diffusion-based ma-nipulation methods. FaceArmor then employs an attention-based softweighting scheme to generate effective adversarial perturbations acrossthese heterogeneous features. By extracting intrinsic attention heatmapsdirectly from the surrogate models, this strategy smoothly decouplescompeting gradients and resolves spatial optimization conflicts. Exten-sive experiments demonstrate that FaceArmor not only preserves visualimperceptibility but also achieves exceptional zero-knowledge transfer-ability, robustly thwarting diverse malicious manipulations across state-of-the-art architectures.

ECCV 2026

Fabric Image Demoiréing Benchmark from Synthesis to Restoration

Pengchao Wei, Xiaojie Guo

Fabric moiré is a sampling-induced aliasing artifact caused by the interaction between fine textile patterns and camera sensor grids, producing structured interference that severely degrades image quality. Unlike screen-induced moiré, which stems from strictly periodic display lattices, fabric moiré is intrinsically more challenging due to the broadband and semi-periodic nature of textile weaves. The heavy spectral overlap between intrinsic texture and aliasing components renders fabric demoiréing substantially more ill-posed. Consequently, existing models trained on screen moiré datasets generalize poorly to these complex textile patterns. Despite its practical importance, fabric image demoiréing remains underexplored and lacks standardized benchmarks. We present the first comprehensive benchmark for fabric image demoiréing. To address the difficulty of acquiring pixel-aligned real-world pairs, we develop a physically motivated synthesis framework and construct a large-scale dataset comprising 16,050 paired multi-resolution fabric images with controllable aliasing severity. Furthermore, we customize a baseline model, which establishes promising performance on the proposed benchmark dataset with strong generalization ability. Our benchmark provides a standardized platform for advancing research in fabric image demoiréing.

ECCV 2026

Entropy-Controlled Flow Matching

Chika Maduabuchi

Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs). Despite strong empirical performance, standard flow-matching objectives do not directly control the information geometry of the trajectory, allowing low-entropy bottlenecks that can transiently deplete semantic modes. We propose Entropy-Controlled Flow Matching (ECFM): a constrained variational principle over continuityequation paths enforcing a global entropy-rate budget d H(µ ) ≥ −λ. dt t ECFM is a convex optimization in Wasserstein space with a KKT/Pontryagin system, and admits a stochastic-control representation equivalent to a Schrödinger bridge with an explicit entropy multiplier. In the pure transport regime, ECFM recovers entropic OT geodesics and Γ-converges to classical OT as λ → 0. We further obtain certificate-style mode-coverage and density-floor guarantees with Lipschitz stability, and construct nearoptimal collapse counterexamples for unconstrained flow matching.

ECCV 2026

EgoCogNav: Cognition-aware Human Egocentric Navigation

Zhiwen Qiu, Ziang Liu, Wenqian Niu, Tapomayukh Bhattacharjee, Saleh Kalantari

Modeling the cognitive and experiential factors of humannavigation is central to deepening our understanding of human–environmentinteraction and to enabling safe social navigation and effective assis-tive wayfinding. Most existing methods focus on forecasting motionsin fully observed scenes and often neglect human factors that capturehow people feel and respond to space. To address this gap, we proposeEgoCogNav, a multimodal egocentric navigation framework that jointlyforecasts perceived path uncertainty, trajectories and head motion fromegocentric video, gaze, and motion history. To facilitate research in thefield, we introduce the Cognition-aware Egocentric Navigation (CEN)dataset consisting of 6 hours real-world egocentric recordings capturingdiverse navigation behaviors in real-world scenarios. Experiments showthat EgoCogNav learns the perceived uncertainty that strongly correlateswith human-like behaviors such as scanning, hesitation, and backtrack-ing while improving trajectory and head-motion forecasting on held-outnavigation recordings. Project page: https://calvinzqiu.github.io/egocognav-project/

ECCV 2026

3D-ReGen: A Unified 3D Geometry Regeneration Framework

Geon Yeong Park, Roman Shapovalov, Rakesh Ranjan, Jong Chul Ye, Andrea Vedaldi, Thu Nguyen-Phuoc

We consider the problem of regenerating 3D objects from2D images and initial 3D shapes. Most 3D generators operate in a one-shot fashion, converting text or images to a 3D object with limited con-trollability. We introduce instead MeshReGen, a 3D regenerator that isconditioned on an initial 3D shape. This conceptually simple formula-tion allows us to support numerous useful tasks, including 3D enhance-ment, reconstruction, and editing. MeshReGen uses a new condition-ing mechanism based on VecSet, which allows the regenerator to up-date or improve the input geometry with consistent fine-grained details.MeshReGen learns a widely applicable regeneration prior from o!-the-shelf 3D datasets via self-supervised pretext tasks and augmentations,without additional annotations. We evaluate both the geometric consis-tency and fine-grained quality of MeshReGen, achieving state-of-the-artperformance in controllable 3D generation across several tasks.Query pointsConditional ImagesCond.(a) Architecture Latents !! PE❌…3D Coarse Cond.DINO V2 OutputDiT blocks⟳ ×#Zero-InitVAE Proj. VAEEncoder C DecoderCross attnSelf attnMLP… … …RefinedLatents…Random(b) Applications LatentsCoarse Mesh Enhancement Partial Point Cloud Reconstruction Masked Mesh EditingFig. 2: Overview. MeshReGen takes both 2D image and initial 3D geometry as input,enabling explicit control over global geometry (e.g., pose, coarse shape) while improvingfine-grained details. The 3D condition is encoded as VecSet latents (z L ) that compactlyrepresent the global geometry. After taking the sum with the positional embeddings,these conditioning and random latents are di!used by a DiT into enhanced latents andthen decoded into a complete, high-quality 3D shape.

ECCV 2026

Egocentric World Model for Photorealistic Hand Object Interaction Synthesis

Dayou Li, Lulin Liu, Bangya Liu, Shijie Zhou, Jiu Feng, Ziqi Lu, Minghui Zheng, Chenyu You, Zhiwen Fan

To serve as a scalable data source for embodied AI, worldmodels should act as true simulators that infer interaction dynamicsstrictly from user actions, rather than mere conditional video genera-tors relying on privileged future object states. In this context, egocentricHand Object Interaction (HOI) world models are critical for predictingphysically grounded first-person rollouts. However, building such modelsis profoundly challenging due to rapid head motions, severe occlusions,and high-DoF hand articulations that abruptly alter contact topolo-gies. Consequently, existing approaches often circumvent these physicschallenges by resorting to conditional video generation with access toknown future object trajectories. We introduce EgoHOI, an egocentricHOI world model that breaks away from this shortcut to simulate pho-torealistic, contact-consistent interactions from action signals alone. Toensure physical accuracy without future-state inputs, EgoHOI distillsgeometric and kinematic priors from 3D estimates into physics-informedembeddings. These embeddings regularize the egocentric rollouts towardphysically valid dynamics. Experiments on the HOT3D dataset demon-strate consistent gains over strong baselines, and ablations validate theeffectiveness of our physics-informed design.

ECCV 2026

Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping

Jinho Kim, Jinwoo Kim, Seon Joo Kim

We propose DOME-HDR, a dual-output multi-exposure HDRreconstruction framework that jointly produces a perceptually balancedSDR image and a consistent HDR image via gain map inverse tone map-ping. Given three bracketed LDR inputs, DOME-HDR first synthesizesa base SDR using a LoRA-adapted latent diffusion model. A dual cross-attention fusion module injects complementary structural and color cuesfrom the under- and over-exposed images while anchoring on the mid ex-posure for stability. The synthesized SDR then guides HPGM, our HDRPrior-guided Gain Map network, to predict a spatially varying gain mapfor reliable dynamic-range expansion. We evaluate on Kalantari, Tel, andChallenge123 using both full-reference and no-reference metrics, whereDOME-HDR achieves state-of-the-art HDR reconstruction quality; abla-tions further confirm the effectiveness of dual cross-attention and SDR-guided gain map estimation.

ECCV 2026

Dual-Margin Embedding for Fine-Grained Long-Tailed Plant Taxonomy

Cheng Yaw Low, Heejoon Koo, Jaewoo Park, Meeyoung Cha

Taxonomic classification of ecological families, genera, andspecies underpins biodiversity monitoring and conservation. Existing com-puter vision methods typically address fine-grained recognition and long-tailed learning in isolation. However, additional challenges such as spa-tiotemporal domain shift, hierarchical taxonomic structure, and previ-ously unseen taxa often co-occur in real-world deployment, leading tobrittle performance under open-world conditions. We propose TaxoNet,an embedding learning framework with a theoretically grounded dual-margin objective that reshapes class decision boundaries under classimbalance to improve fine-grained discrimination while strengtheningrare-class representation geometry. We evaluate TaxoNet in open-worldsettings that capture co-occurring recognition challenges. Leveraging di-verse plant datasets, including Google Auto-Arborist (urban tree im-agery), iNaturalist (Plantae observations across heterogeneous ecosys-tems), and NAFlora-Mini (herbarium collections), we demonstrate thatTaxoNet consistently outperforms strong baselines, including multimodalfoundation models.

ECCV 2026

Doe-2: 3D Representation World Model for Unified Driving Scene Forecasting

Dong Zhuo, Wenzhao Zheng, Sicheng Zuo, Yuanhui Huang, Siming Yan, Lu Hou, Jie Zhou, Jiwen Lu

Forecasting future scene evolutions is crucial for autonomousdriving safety. Most existing driving world models focus on appearancegeneration and fail to model geometric and semantic evolutions. In thispaper, we propose a native 3D world model, Doe-2, to forecast the com-prehensive scene evolutions in a unified 3D latent representation space.This representation contains both appearance, geometry, and semanticinformation and can be decoded into multi-view RGB, depth, semantics,and 3D occupancy. For efficiency, we adopt an autoregressive transformerarchitecture to generate all latents for the next scene in one pass and thenuse a lightweight diffusion head to refine them for better fidelity. Operat-ing on the compact 3D latent space, our model supports efficient futurerollouts conditioned on different actions. Extensive experiments on thenuScenes dataset show the ability of Doe-2 to efficiently and comprehen-sively forecast future driving scenes. Despite being trained from scratchwith only 700 scenes, Doe-2 already shows high-quality scene generationand good generalization with action control ability.

ECCV 2026

ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection

Ningning Han, Lei Fan, Jia Guo, Yunkang Cao, Xiu Su, Feng Cao, Donglin Di, Tonghua Su

The deployment of Industrial Anomaly Detection (IAD) inreal-world manufacturing frequently encounters a challenging cold-startbottleneck, in which limited normal samples fail to represent the fullnormal distribution and only a few anomalies are available. Under sucha regime, existing methods struggle to form compact normal boundariesand fail to effectively exploit supervised signals from rare defects. To ad-dress this challenge, we propose Anomaly-Rectified Cold-start AD (Ar-cAD), a plug-and-play calibration framework for reconstruction-basedIAD baselines. ArcAD follows a push–pull learning paradigm to constructa compact and discriminative normal boundary under data scarcity. Onthe one hand, ArcAD projects limited normal samples onto a hypersphereand pulls them into multiple compact clusters to maximize coverage ofthe normal manifold. On the other hand, it synthesizes pseudo-anomalieson the hypersphere and leverages real anomalies to push the boundaryinward and sharpen anomaly discrimination. Extensive experiments onMVTec-AD, VisA, Real-IAD, and MANTA demonstrate that ArcADsignificantly outperforms state-of-the-art supervised and unsupervisedmethods in both single-class and multi-class settings under cold-startconditions. Code is available at: https://github.com/LGC-AD/ArcAD.

ECCV 2026

DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models

Francesco Taioli, Daniel Coelho, Iaroslav Melekhov, Roberto Alcover-Couso, Jose Saiz, Virginia Arguedas, Artur Bekasov

Despite remarkable progress in text-guided image editing, gen-erative models frequently fail to preserve visual object consistency, definedas the preservation of a subject’s key attributes throughout the editingprocess. We address this limitation through three contributions. First, weintroduce ABO-Edit, a dataset specifically designed to study object con-sistency, comprising over 12,000 triplets of source images, editing prompts,and high-quality target images rendered from artist-designed 3D assets,with multi-view coverage and human-verified quality control. Second, weuncover an overlooked property of image-editing rectified flow models: theconditioning embedding space, not directly supervised during training,encodes a prediction of the final generated image even at high noise levels.Third, exploiting this finding, we propose FlowMirror, a parameter-freeauxiliary loss that supervises this conditioning embedding space. Withoutarchitectural changes, our method improves generation quality acrossseveral metrics over baselines. Page: francescotaioli.github.io/DiTailed

Keep browsing

More papers from top AI conferences

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