CVPR 2026 Papers

Recent perception-generalist approaches based on language models have achieved state-of-the-art results across diverse tasks, including 3D scene layout estimation and 3D object detection, via unified architecture and interface. However, these approaches rely on autoregressive next-token prediction, which is inherently slow. In this work, we introduce Fast SceneScript, a novel structured language model for accurate and efficient 3D scene understanding. Our method employs multi-token prediction (MTP) to reduce the number of autoregressive iterations and significantly accelerate inference. While MTP improves speed, unreliable token predictions can significantly reduce accuracy. To filter out unreliable tokens, we adapt self-speculative decoding (SSD) for structured language models and introduce confidence-guided decoding (CGD) with an improved scoring mechanism for token reliability. Furthermore, we design a parameter-efficient mechanism that reduces the parameter overhead of MTP. Extensive experiments on synthetic and real-world benchmarks demonstrate that Fast SceneScript can generate up to 9 tokens per decoder inference step without compromising accuracy, while adding only 7.5% additional parameters.

The performance of mean-based prototypical methods in few-shot learning is frequently compromised by noise and hard positives, where entangled feature representations cause prototype instability. We present a novel "Filter-Repair-Expand" framework grounded in Determinantal Point Process (DPP) theory. The method leverages DPP as its core logic, employing it to estimate sample confidence to filter anomalous samples from the initial set, guide a diffusion process via volume-maximization to enhance the sample representation, and subsequently maximize the volume of synergistic disentangled subspaces, constructing robust and diverse prototype subspaces. Experimental results establish new state-of-the-art performance on multiple benchmarks, demonstrating significant gains in few-shot learning robustness. Code is available at https://github.com/24sleeping90/DDSF.

Recently, 3D Gaussian Splatting and its derivatives have achieved significant breakthroughs in large-scale scene reconstruction. However, how to efficiently and stably achieve high-quality geometric fidelity remains a core challenge. To address this issue, we introduce MetroGS, a novel Gaussian Splatting framework for efficient and robust reconstruction in complex urban environments. Our method is built upon a distributed 2D Gaussian Splatting representation as the core foundation, serving as a unified backbone for subsequent modules. To handle potential sparse regions in complex scenes, we propose a structured dense enhancement scheme that utilizes SfM priors and a pointmap model to achieve a denser initialization, while incorporating a sparsity compensation mechanism to improve reconstruction completeness. Furthermore, we design a progressive hybrid geometric optimization strategy that organically integrates monocular and multi-view optimization to achieve efficient and accurate geometric refinement. Finally, to address the appearance inconsistency commonly observed in large-scale scenes, we introduce a depth-guided appearance modeling approach that learns spatial features with 3D consistency, facilitating effective decoupling between geometry and appearance and further enhancing reconstruction stability. Experiments on large-scale urban datasets demonstrate that MetroGS achieves superior geometric accuracy, rendering quality, offering a unified solution for high-fidelity large-scale scene reconstruction. Project page: https://m3phist0.github.io/MetroGS.

Pixel-wise capabilities are essential for building interactive intelligent systems. However, pixel-wise multi-modal LLMs (MLLMs) remain difficult to scale due to complex region-level encoders, specialized segmentation decoders, and incompatible training objectives. To address these challenges, we present SAMTok, a discrete mask tokenizer that converts any region mask into two special tokens and reconstructs the mask from these tokens with high fidelity. By treating masks as a new language, SAMTok enables base MLLMs (such as the QwenVL series) to learn pixel-wise capabilities through standard next-token prediction and simple reinforcement learning, without architectural modifications and specialized loss design. SAMTok builds on SAM2 and is trained on 209M diverse masks using a mask encoder and residual vector quantizer to produce discrete, compact, and information-rich tokens. With 5M SAMTok-formatted mask understanding and generation data samples, QwenVL-SAMTok attains state-of-the-art or comparable results on region captioning, region VQA, grounded conversation, referring segmentation, scene graph parsing, and multi-round interactive segmentation. We further introduce a textual answer-matching reward that enables efficient reinforcement learning for mask generation, delivering substantial improvements on GRES and GCG benchmarks. Our results demonstrate a scalable and straightforward paradigm for equipping MLLMs with strong pixel-wise capabilities.

Audio-Visual Speech Recognition (AVSR) has achieved remarkable progress in offline conditions, yet its robustness in real-world video conferencing (VC) remains largely unexplored. This paper presents the first systematic evaluation of state-of-the-art AVSR models across mainstream VC platforms, revealing severe performance degradation caused by transmission distortions and spontaneous human hyper-expression. To address this gap, we construct MLD-VC, the first multimodal dataset tailored for VC, comprising 31 speakers, 22.79 hours of audio-visual data, and explicit use of the Lombard effect to enhance human hyper-expression. Through comprehensive analysis, we find that speech enhancement algorithms are the primary source of distribution shift, which alters the first and second formants of audio. Interestingly, we find that the distribution shift induced by the Lombard effect closely resembles that introduced by speech enhancement, which explains why models trained on Lombard data exhibit greater robustness in VC. Fine-tuning AVSR models on MLD-VC mitigates this issue, achieving an average 17.5% reduction in CER across several VC platforms. Our findings and dataset provide a foundation for developing more robust and generalizable AVSR systems in real-world video conferencing. MLD-VC is available at https://huggingface.co/datasets/nccm2p2/MLD-VC.

Cardiovascular disease (CVD) diagnosis relies heavily on electrocardiograms (ECGs). However, most existing self-supervised uni-modal methods suffer from limited representational capacity, while multi-modal frameworks are hindered by coarse-grained semantic alignment across modalities, thus restricting their generalizability in clinical settings. To address these limitations, we propose TAMER, a Tri-modal contrastive Alignment and Multi-scale Embedding Refinement framework that jointly models ECG recordings, spectrograms, and diagnostic reports. TAMER is composed of three key components: First, the tri-modal feature encoding and projection (TFEP) module employs modality-specific encoders to extract global and local features from ECG recordings, spectrograms, and diagnostic reports, and projects them into latent spaces. Then, the global-local temporal-spectral alignment (GLTSA) module captures complementary rhythm- and wave-level characteristics via contrastive alignment and attentive interaction between temporal and spectral modalities. Finally, the report-aware alignment and refinement (RAAR) module performs diagnostic-level alignment and wave-level refinement with clinical reports, enabling semantic enrichment of ECG representations.Extensive experiments on three public ECG datasets demonstrate that TAMER achieves state-of-the-art zero-shot classification performance (AUC: 81.2%) and strong cross-domain generalization (AUC: 83.1%), outperforming existing uni-modal and multi-modal baselines methods.The source code is available at https://github.com/zhouxw12345/TAMER.

Success in generative modeling across language, image, and video demonstrates that large, well-curated datasets are the key driver for building capable models. 3D Human motion, however, has lagged behind, constrained by an unsatisfying choice between small, high-fidelity motion capture datasets and large-scale in-the-wild collections dominated by static or low-quality sequences.We introduce RoMo, a rich, large-scale, carefully curated dataset of in-the-wild human motions that resolves these tradeoffs. To ensure quality, we introduce a taxonomy-aware filtering pipeline that aggressively removes static and artifact-prone sequences. Every sequence is annotated with detailed captions and organized by a novel three-level semantic taxonomy. This hierarchical structure provides the first benchmark for fine-grained, per-category evaluation, revealing model strengths and weaknesses obscured by global metrics. We demonstrate that models trained on RoMo achieve state-of-the-art fidelity and diversity while gaining a superior understanding of complex, subtle text prompts. Finally, we release the Motion Toolbox to standardize metrics, data conversion, and visualization, establishing a foundation for reproducible and interpretable motion generation research.

A faithful decision-making process requires models to ground human-understandable concepts both spatially (where they appear in the image) and causally (how they influence the prediction). Recent advances in Vision-Language Models (VLMs) enable concept-level alignment and have inspired Concept Bottleneck Models (CBMs), which explain predictions by mapping image representations to human-understandable concepts, allowing users to trace decisions through explicit semantic reasoning. However, existing CBMs suffer from two key inconsistencies. First, semantic inconsistency: VLMs often fail to localize fine-grained part-attribute concepts, producing noisy or incomplete masks. Second, object inconsistency: object-agnostic concepts such as "head: streamlined front profile" may describe multiple categories (e.g., fish or human); without enforcing object identity, non-targeted regions can introduce spurious evidence that corrupts the bottleneck representation. To address these challenges, we propose a new Object-Aware Concept Bottleneck Model (OA-CBM) that jointly enforces semantic- and object-level consistency. Specifically, (1) we redefine concepts as part-attribute pairs to enhance VLM robustness at the semantic level, and (2) introduce class-agnostic object clustering to suppress irrelevant visual evidence. We further annotate two grounding datasets with part-attribute descriptions and conduct extensive experiments. Results demonstrate that OA-CBM produces more faithful and robust explanations while maintaining competitive predictive performance.

Estimating dense 2D optical flow and 3D scene flow is essential for dynamic scene understanding. Recent work combines images, LiDAR, and event data to jointly predict 2D and 3D motion, yet most approaches operate in separate heterogeneous feature spaces. Without a shared latent space that all modalities can align to, these systems rely on multiple modality-specific blocks, leaving cross-sensor mismatches unresolved and making fusion unnecessarily complex. Event cameras naturally provide a spatiotemporal edge signal, which we can treat as an intrinsic edge field to anchor a unified latent representation, termed the Event Edge Space. Building on this idea, we introduce x^2-Fusion, which reframes multimodal fusion as representation unification: event-derived spatiotemporal edges define an edge-centric homogeneous space, and image and LiDAR features are explicitly aligned in this shared representation. Within this space, we perform reliability-aware adaptive fusion to estimate modality reliability and emphasize stable cues under degradation. We further employ cross-dimension contrast learning to tightly couple 2D optical flow with 3D scene flow. Extensive experiments on both synthetic and real benchmarks show that x^2-Fusion achieves state-of-the-art accuracy under standard conditions and delivers substantial improvements in challenging scenarios.

The widespread use of smartphones has made photography ubiquitous, yet a clear gap remains between ordinary users and professional photographers, who can identify aesthetic issues and provide actionable shooting guidance during capture. We define this capability as aesthetic guidance (AG) --- an essential but largely underexplored domain in computational aesthetics. Existing multimodal large language models (MLLMs) primarily offer overly positive feedback, failing to identify issues or provide actionable guidance. Without AG capability, they cannot effectively identify distracting regions or optimize compositional balance, thus also struggling in aesthetic cropping, which aims to refine photo composition through reframing after capture. To address this, we introduce AesGuide, the first large-scale AG dataset and benchmark with 10,748 photos annotated with aesthetic scores, analyses, and guidance. Building upon it, we propose Venus, a two-stage framework that first empowers MLLMs with AG capability through progressively complex aesthetic questions and then activates their aesthetic cropping power via CoT-based rationales. Extensive experiments show that Venus substantially improves AG capability and achieves state-of-the-art (SOTA) performance in aesthetic cropping, enabling interpretable and interactive aesthetic refinement across both stages of photo creation. Code is available at https://github.com/PKU-ICST-MIPL/Venus_CVPR2026.

Precise motion timing (PMT) is crucial for swift motion analysis. A millisecond difference may determine victory or defeat in sports competitions. Despite substantial progress in human pose estimation (HPE), PMT remains largely overlooked by the HPE community due to the limited availability of high-temporal-resolution labeled datasets. Today, PMT is achieved using high-speed RGB cameras in specialized scenarios such as the Olympic Games; however, their high costs, light sensitivity, bandwidth, and computational complexity limit their feasibility for daily use. We developed FlashCap, the first flashing LED-based MoCap system for PMT. With FlashCap, we collect a millisecond-resolution human motion dataset, FlashMotion, comprising the event, RGB, LiDAR, and IMU modalities, and demonstrate its high quality through rigorous validation. To evaluate the merits of FlashMotion, we perform two tasks: precise motion timing and high-temporal-resolution HPE. For these tasks, we propose ResPose, a simple yet effective baseline that learns residual poses based on events and RGBs. Experimental results show that ResPose reduces pose estimation errors by 40% and achieves millisecond-level timing accuracy, enabling new research opportunities. The dataset and code will be shared with the community.

Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimization, known camera calibration, or short frame windows, making them slow and impractical. We revisit this problem from a feedforward perspective and introduce Driving Gaussian Grounded Transformer (DGGT), a unified framework for pose-free dynamic scene reconstruction. We note that the existing formulations, treating camera pose as a required input, limit flexibility and scalability. Instead, we reformulate pose as an output of the model, enabling reconstruction directly from sparse, unposed images and supporting an arbitrary number of views for long sequences. Our approach jointly predicts per-frame 3D Gaussian maps and camera parameters, disentangles dynamics with a lightweight dynamic head, and preserves temporal consistency with a lifespan head that modulates visibility over time. A diffusion-based rendering refinement further reduces motion/interpolation artifacts and improves novel-view quality under sparse inputs. The result is a single-pass, pose-free algorithm that achieves state-of-the-art performance and speed. Trained and evaluated on large-scale driving benchmarks (Waymo, nuScenes, Argoverse2), our method outperforms prior work both when trained on each dataset and in zero-shot transfer across datasets, and it scales well as the number of input frames increases.

Monocular 3D pose estimation is fundamentally ill-posed due to depth ambiguity and occlusions, thereby motivating probabilistic methods that generate multiple plausible 3D pose hypotheses. In particular, diffusion-based models have recently demonstrated strong performance, but their iterative denoising process typically requires many timesteps for each prediction, making inference computationally expensive. In contrast, we leverage Flow Matching (FM) to learn a velocity field defined by an Ordinary Differential Equation (ODE), enabling efficient generation of 3D pose samples with only a few integration steps. We propose a novel generative pose estimation framework, FMPose3D, that formulates 3D pose estimation as a conditional distribution transport problem. It continuously transports samples from a standard Gaussian prior to the distribution of plausible 3D poses conditioned only on 2D inputs. Although ODE trajectories are deterministic, FMPose3D naturally generates various pose hypotheses by sampling different noise seeds. To obtain a single accurate prediction from those hypotheses, we further introduce a Reprojection-based Posterior Expectation Aggregation (RPEA) module, which approximates the Bayesian posterior expectation over 3D hypotheses. FMPose3D surpasses existing methods on the widely used human pose estimation benchmarks Human3.6M and MPI-INF-3DHP, and further achieves state-of-the-art performance on the 3D animal pose datasets Animal3D and CtrlAni3D, demonstrating strong performance across both 3D pose domains. The code is available at https://github.com/AdaptiveMotorControlLab/FMPose3D.

Embodied Question Answering (EQA) requires an agent to interpret language, perceive its environment, and navigate within 3D scenes to produce responses. Existing EQA benchmarks assume that every question must be answered, but embodied agents should know when they do not have sufficient information to answer. In this work, we focus on a minimal requirement for EQA agents, abstention: knowing when to withhold an answer. From an initial study of 500 human queries, we find that 32.4% contain missing or underspecified context. Drawing on this initial study and cognitive theories of human communication errors, we derive five representative categories requiring abstention: actionability limitation, referential underspecification, preference dependence, information unavailability, and false presupposition. We augment OpenEQA by having annotators transform well-posed questions into ambiguous variants outlined by these categories. The resulting dataset, AbstainEQA, comprises 1,636 annotated abstention cases paired with 1,636 original OpenEQA instances for balanced evaluation. Evaluating on AbstainEQA, we find that even the best frontier model only attains 42.79% abstention recall, while humans achieve 91.17%. We also find that scaling, prompting, and reasoning only yield marginal gains, and that fine-tuned models overfit to textual cues. Together, these results position abstention as a fundamental prerequisite for reliable interaction in embodied settings and as a necessary basis for effective clarification.

Training machine learning models on massive datasets is expensive and time-consuming. Dataset distillation addresses this by creating a small synthetic dataset that achieves the same performance as the full dataset. Recent methods use diffusion models to generate distilled data, either by promoting diversity or matching training gradients. However, existing approaches produce redundant training signals, where samples convey overlapping information. Empirically, disjoint subsets of distilled datasets capture 80-90% overlapping signals. This redundancy stems from optimizing visual diversity or average training dynamics without accounting for similarity across samples, leading to datasets where multiple samples share similar information rather than complementary knowledge. We propose learnability-driven dataset distillation, which constructs synthetic datasets incrementally through successive stages. Starting from a small set, we train a model and generate new samples guided by learnability scores that identify what the current model can learn from, creating an adaptive curriculum. We introduce Learnability-Guided Diffusion (LGD), which balances training utility for the current model with validity under a reference model to generate curriculum-aligned samples. Our approach reduces redundancy by 39.1%, promotes specialization across training stages, and achieves state-of-the-art results on ImageNet-1K (60.1%), ImageNette (87.2%), and ImageWoof (72.9%).

Radiology report generation (RRG) aims to automatically produce clinically faithful reports from chest X-ray images. Prevailing work typically follows a scale-driven paradigm, by multi-stage training over large paired corpora and oversized backbones, making pipelines highly data- and compute-intensive. In this paper, we propose Oracle-educated GRPO (OraPO) with a FactScore-based reward (FactS) to tackle the RRG task under constrained budgets. OraPO enables single-stage, RL-only training by converting failed GRPO explorations on rare or difficult studies into direct preference supervision via a lightweight oracle step. FactS grounds learning in diagnostic evidence by extracting atomic clinical facts and checking entailment against ground-truth labels, yielding dense, interpretable sentence-level rewards. Together, OraPO and FactS create a compact and powerful framework that significantly improves learning efficiency on clinically challenging cases, setting the new SOTA performance on the CheXpert Plus dataset (0.341 in F1) with 2-3 orders of magnitude less training data using a small base VLM on modest hardware.

Vision-based end-to-end (E2E) driving has garnered interest in the research community due to its scalability and synergy with multimodal large language models (MLLMs). However, current E2E driving benchmarks primarily feature nominal scenarios paired with existing open-loop evaluation metrics that fall short in capturing the multimodal nature of driving or effectively evaluating performance in long-tail scenarios. To address these gaps, we introduce the Waymo Open Dataset for End-to-End Driving (WOD-E2E). WOD-E2E contains 4,021 driving segments (approximately 12 hours), specifically curated for challenging long-tail scenarios that are rare in daily life with an occurring frequency of less than 0.03%. Each segment in WOD-E2E includes the high-level routing information, ego states, and 360-degree camera views from 8 surrounding cameras. To evaluate E2E driving performance on these long-tail situations, we propose a novel open-loop evaluation metric: Rater Feedback Score (RFS). Unlike conventional distance-based metrics, RFS measures how closely a predicted trajectory matches rater-annotated trajectory preference labels. WOD-E2E includes rater preference labels for validation, and a separate held out test set is used for the 2025 WOD-E2E Challenge benchmark leaderboard.

This paper presents a new dataset for Novel View Synthesis, generated from a high-quality, animated film with stunning realism and intricate detail. Our dataset captures a variety of dynamic scenes, complete with detailed textures, lighting, and motion, making it ideal for training and evaluating cutting-edge 4D scene reconstruction and novel view generation models. In addition to high-fidelity RGB images, we provide multiple complementary modalities, including depth, surface normals, object segmentation and optical flow, enabling a deeper understanding of scene geometry and motion. The dataset is organised into three distinct benchmarking scenarios: a dense multi-view camera setup, a sparse camera arrangement, and monocular video sequences, enabling a wide range of experimentation and comparison across varying levels of data sparsity. With its combination of visual richness, high-quality annotations, and diverse experimental setups, this dataset offers a unique resource for pushing the boundaries of view synthesis and 3D vision.

3D Gaussian Splatting (3DGS) has become a standard approach to reconstruct and render photorealistic 3D head avatars. A major challenge is to relight the avatars to match any scene illumination. For high quality relighting, existing methods require subjects to be captured under complex time-multiplexed illumination, such as one-light-at-a-time (OLAT). We propose a new generalized relightable 3D Gaussian head model that can relight any subject observed in a single- or multi-view images without requiring OLAT data for that subject. Our core idea is to learn a mapping from flat-lit 3DGS avatars to corresponding relightable Gaussian parameters for that avatar. Our model consists of two stages: a first stage that models flat-lit 3DGS avatars without OLAT lighting, and a second stage that learns the mapping to physically-based reflectance parameters for high-quality relighting. This two-stage design allows us to train the first stage across diverse existing multi-view datasets without OLAT lighting ensuring cross-subject generalization, where we learn a dataset-specific lighting code for self-supervised lighting alignment. Subsequently, the second stage can be trained on a significantly smaller dataset of subjects captured under OLAT illumination. Together, this allows our method to generalize well and relight any subject from the first stage as if we had captured them under OLAT lighting. Furthermore, we can fit our model to unseen subjects from as little as a single image, allowing several applications in novel view synthesis and relighting for digital avatars.