CVPR 2026 论文列表

We present WonderZoom, a novel approach to generating 3D scenes with contents across multiple spatial scales from a single image. Existing 3D world generation models remain limited to single-scale synthesis and cannot produce coherent scene contents at varying granularities. The fundamental challenge is the lack of a scale-aware 3D representation capable of generating and rendering content with largely different spatial sizes. WonderZoom addresses this through two key innovations: (1) scale-adaptive Gaussian surfels for generating and real-time rendering of multi-scale 3D scenes, and (2) a progressive detail synthesizer that iteratively generates finer-scale 3D contents. Our approach enables users to "zoom into" a 3D region and auto-regressively synthesize previously non-existent fine details from landscapes to microscopic features. Experiments demonstrate that WonderZoom significantly outperforms state-of-the-art video and 3D models in both quality and alignment, enabling multi-scale 3D world creation from a single image. We show video results and an interactive viewer of generated multi-scale 3D worlds on the website of the supplementary materials.

3D Referring Expression segmentation (3D-RES) is an emerging field that segments 3D objects in point cloud scenes based on given referring expressions. Although existing methods have achieved substantial progress, they primarily focus on semantic cues and often overlook spatial relations, which are essential for segmenting the referred objects in complex 3D scenes, especially those containing multiple visually similar instances. In this paper, we propose Position3D, a novel approach that explicitly incorporates spatial relation modeling into 3D-RES. Specifically, we introduce a spatial-aware query generation module that constructs point proxies by aggregating local context and incorporating spatial relations, from which the most text-relevant are selected as queries. Furthermore, we design a position-guided deformable attention in the decoder, which progressively refines attention to concentrate on the target object under positional relationship guidance. Extensive experiments on two benchmark datasets, i.e., ScanRefer, and Multi3DRefer, validate the effectiveness of the proposed method Position3D.

Small object detection (SOD) plays a vital role in applications such as anti-UAV tasks, yet conventional image-based methods struggle in high-speed scenarios due to the limited frame rate. Event cameras offer a promising alternative by capturing spatiotemporal event streams with microsecond-level temporal resolution. To address the inherent sparsity of small objects in event data, existing methods typically formulate the detection task as semantic segmentation on spatiotemporal point clouds to leverage long-term contextual information. However, these methods often fail to enforce effective spatiotemporal consistency constraints, resulting in fragmented object trajectories. To mitigate these problems, we propose a topology-constrained sparse convolutional network (SpTopoNet), which models the topological structure of moving object trajectories in event point clouds. Our network comprises two key components: a Topology Learning Module (TLM) that discriminates local structures to separate genuine targets from noise, and a Spatial Consistency Module (SCM) that captures long-range spatiotemporal dependencies to enhance trajectory continuity. Additionally, we introduce an event topology-aware loss function that leverages topological correlations to guide the network to maintain structural integrity of target event patterns.Experiments on the benchmark dataset demonstrate the superiority of our method in both detection performance and trajectory completeness.

Diffusion transformer models deliver state-of-the-art image synthesis quality but suffer from prohibitively slow iterative sampling. Although reducing sampling steps accelerates inference, aggressive step schedules often distort intermediate features and degrade sample fidelity. We present GeoRK2, a training-free framework that bridges numerical analysis and information geometry. GeoRK2 couples a second-order Runge-Kutta (RK2) integrator with a curvature-aware geometric flow derived from the model's noise predictions, promoting stable feature evolution under manifold-aware integration. By leveraging an empirical feature covariance-induced metric estimated from activation covariances to capture intrinsic feature geometry, GeoRK2 constrains error propagation under large-step integration while preserving structural fidelity. As a fully plug-and-play method, GeoRK2 requires no retraining and is compatible with mainstream pre-trained diffusion transformers. Comprehensive experiments on image generation and text-to-video generation tasks across representative diffusion backbones (e.g., DiT-XL, HunyuanVideo, and FLUX.1-dev) demonstrate that GeoRK2 achieves 4-5x faster inference than baseline frameworks with only marginal perceptual differences (DFID 0.81), confirming its effectiveness and generality.

**Document QA** requires not only accurate answers but also identifying where each answer is grounded on the page. Most models treat the task as text-only generation, while existing answer grounding methods generate coarse bounding boxes that fail to capture curved text. We introduce **M3Grounder, a hybrid vision-language and segmentation architecture that formulates document grounding as pixel-level segmentation. It produces fine-grained evidence masks** refined by a bleed-suppression loss to prevent spillover. M3Grounder autoregressively generates answer text interleaved with [GROUND] tokens that link individual answer spans to their corresponding evidence regions. Also, **M3Grounder grounds evidence hierarchically across phrase, line, and block levels** using an enclosure loss that enforces spatial containment. We release **GroundingDocQA dataset (200K documents, 2M multi-span and multi-granular QA pairs with pixel-level grounding masks)**, built through a data engine that handles complex layouts, curved-text, and graphics-rich documents. We also release **GroundingDocQA-Bench, a diverse and challenging human-verified benchmark**. M3Grounder sets **a new state of the art in grounded DocVQA, advancing from coarse boxes to hierarchical, fine-grained and contextually grounded evidence.**

Mechanistic interpretability seeks circuits that are both sufficient on their own and necessary to a model's behavior under intervention, yet many circuit-discovery pipelines still rely on manually fixed circuit budgets. We propose a procedure that scores edges with sign-preserving integrated gradients and then chooses a single global cutoff by a performance-retention criterion for circuit selection. This makes circuit size a consequence of retained behavior rather than a manually selected budget. On the Mechanistic Interpretability Benchmark, this retention-calibrated thresholding yields circuits that are competitive on CPR/CMD across multiple tasks and models. On our GPT-2 IOI probability-space diagnostic, it improves sufficiency relative to the EAP-IG baseline while also improving the reported necessity diagnostics. Threshold ablations and stability checks further show that the selected operating point yields the best overall balance between self-sufficiency and necessity-oriented diagnostics.

The YOLO (You Only Look Once) series has been a cornerstone in real-time object detection, renowned for its efficient convolutional design and rapid inference. However, its reliance on convolutional operations inherently limits its ability to capture long-range dependencies and rich contextual information, leading to suboptimal performance in complex scenes. Recently, SSM (State Space Models) have emerged as an efficient alternative to attention mechanisms, offering global representation with linear time complexity. In this paper, we propose AKCMamba-YOLO, a novel object detector that incorporates SSM into the YOLO architecture. We introduce 3CAKCMamba and 4CAKCMamba modules to a novel object detection framework, enabling enhanced channel interaction and cross-layer semantic fusion. This design improves multi-scale feature modeling while maintaining computational efficiency. To support safety-critical applications, we provide railway pedestrian Detection datasets with 2,975 annotated images under complex scenarios. Experiments on COCO2017, power tower foreign object detection datasets, and our custom dataset show that AKCMamba-YOLO achieves superior accuracy and speed compared to state-of-the-art baselines, making it well-suited for real-time and resource-constrained environments.

Open-set semi-supervised learning (OSSL) has achieved notable progress in exploiting unlabeled data, yet most existing methods overlook the distinct sensitivities of in-distribution (ID) and out-of-distribution (OOD) samples to semantic-preserving perturbations, resulting in suboptimal model performance. To address this limitation, we propose Perturbation-Aware Filtering (PAF), which leverages the behavioral difference between ID and OOD samples under perturbations and extends it into a representation-level signal for reliable OOD filtering. Specifically, PAF identifies OOD samples by measuring the representation instability under semantic-preserving perturbations. We then integrate PAF into a carefully designed two-stage training framework, allowing the model to exploit abundant unlabeled data in the first stage and gradually adapt to the open-set setting with limited labels in the second stage. Extensive experimental results on widely-used OSSL benchmarks demonstrate that our proposed PAF approach achieves superior performance compared to state-of-the-art (SOTA) OSSL methods. Our code is available at https://github.com/njustkmg/CVPR26-PAF.

Human action recognition (HAR) in low-light environments remains challenging due to degraded visibility, illumination variance, and loss of appearance cues. We introduce DarkAct, a large-scale and high-quality RGB-thermal video dataset purpose-built for multimodal action recognition under low illumination. DarkAct contains 12,778 paired RGB-thermal videos covering 27 human actions across diverse viewpoints and scenes, offering a novel and comprehensive benchmark for understanding human actions in dark environments. We conduct extensive experiments on DarkAct, systematically benchmarking unimodal HAR models, multimodal fusion frameworks, and vision-language foundation models. Their limited performance on DarkAct underscores the urgent need for more robust perception systems under adverse illumination. To address this, we propose DarkAct-Net, an RGB-thermal fusion framework that enhances human-centric representation and achieves adaptive cross-modal fusion, enabling robust and fine-grained action recognition across diverse lighting conditions. Dataset and code are available at https://github.com/darkact-creator/DarkAct.git.

Parameter Efficient Fine-Tuning (PEFT) is a key technique for adapting a large pretrained model to downstream tasks by fine-tuning only a small number of parameters. Recent methods based on Fourier transforms have further reduced the fine-tuned parameters scale by only fine-tuning a few spectral coefficients. Its basic assumption is that the weight change \Delta W is a spatial-domain matrix with a sparse spectrum. However, in this paper, we observe that the spectrum of weight change is not sparse, but instead distributed like power-uniform. This fact implies that fine-tuning only a few spectral coefficients is insufficient to accurately model the weight change \Delta W with uniform spectrum.To address this issue, we propose to seek an invertible transformation that can transform a latent spatial-domain matrix with sparse spectrum to the weight change, and then perform PEFT on such sparse spectrum domain with few spectral coefficients, called \text S ^2\text FT . To seek such transformation, we first pre-estimate a coarse weight change as a prior. Then, inspired by that sparse spectrum often correspond to locally smooth spatial structures, we regard this transformation as a row and column rearrangement operation on the pre-estimated weight change that smooth spatial structures while keep the structure information of neurons.Finally, we propose to solve the rearrangement search problem in a simple nearest neighbor search manner, thereby obtaining the invertible transformation. Extensive results show our \text S ^2\text FT achieves superior performance by only using 0.08% training parameters.

Humans perceive the 3D world from limited 2D observations. While recent feed-forward generalizable 3D reconstruction models can recover structures from sparse images, they typically represent only observed regions, leaving unseen geometry unmodeled. This raises a fundamental question: Can we infer complete 3D structure from partial observations? We present RnG (Reconstruction and Generation), a feed-forward Transformer that unifies reconstruction and generation by predicting an implicit, complete 3D representation. RnG introduces a reconstruction-guided causal attention mechanism that separates reconstruction and generation at the attention level while treating the KV-cache as an implicit 3D representation. Arbitrary poses can efficiently query this cache to render high-fidelity RGBD outputs. RnG accurately reconstructs visible geometry while generating plausible unseen structures and appearance. It achieves state-of-the-art performance in generalizable 3D reconstruction and novel view generation, while being efficient enough for real-time interactive applications.

We introduce LaviGen, a framework that repurposes 3D generative models for 3D layout generation. Unlike previous methods that infer object layouts from textual descriptions, LaviGen operates directly in the native 3D space, formulating layout generation as an autoregressive process that explicitly models geometric relations and physical constraints among objects, producing coherent and physically plausible 3D scenes. To further enhance this process, we propose an adapted 3D diffusion model to integrate scene, object, and instruction information and employ a dual-guidance self-rollout distillation mechanism to improve efficiency and spatial accuracy. Extensive experiments on the LayoutVLM benchmark show LaviGen achieves superior 3D layout generation performance, with 19% higher physical plausibility than the state of the art and 65% faster computation. We will release our code publicly.

Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-language models (VLMs). However, its outcome-level supervision is too coarse to diagnose and correct errors within the reasoning chain. To this end, we propose Perceval, a process reward model (PRM) that enables token-level error grounding, which can extract image-related claims from the response and compare them one by one with the visual evidence in the image, ultimately returning claims that contain perceptual errors. Perceval is trained with perception-intensive supervised training data. We then integrate Perceval into the RL training process to train the policy models. Specifically, compared to traditional GRPO, which applies sequence-level advantages, we apply token-level advantages by targeting penalties on hallucinated spans identified by Perceval, thus enabling fine-grained supervision signals. In addition to augmenting the training process, Perceval can also assist VLMs during the inference stage. Using Perceval, we can truncate the erroneous portions of the model's response, and then either have the model regenerate the response directly or induce the model to reflect on its previous output. This process can be repeated multiple times to achieve test-time scaling. Experiments show significant improvements on benchmarks from various domains across multiple reasoning VLMs trained with RL. For test-time scaling, it also demonstrates consistent performance gains over other strategies, such as major voting. Our code and data will be publicly released.

The transition of Retrieval-Augmented Generation (RAG) from offline video analysis to online, streaming scenarios presents a set of critical, unexplored challenges. These include the need for on-the-fly semantic segmentation of continuous video, the inherent tension between low-latency processing and high-quality knowledge extraction, and the demand for query-specific temporal reasoning. We propose StreamRAG, a novel framework designed to overcome these hurdles. StreamRAG is built upon three core technical pillars: (1) a Stream Event Segmentation (SES) module that performs real-time boundary detection to chunk the stream into meaningful units; (2) a Token-Reusing Accelerator that drastically cuts down captioning latency by leveraging computational overlap between consecutive frames; and (3) a Dynamic Retrieval Gate that modulates the retrieval scope and strategy based on the query's temporal sensitivity and contextual similarity. Empirical evaluation confirms that StreamRAG establishes a new state-of-the-art, delivering superior accuracy with minimal latency in streaming video comprehension.

Effective human behavior modeling requires a representation of the human body movement that capitalizes on its compositionality. We propose a hierarchical representation consisting of Action Atoms that capture the atomic joint movements and Action Motifs that are formed by their temporal compositions and encode similar body movements found across different overall human actions. We derive A4Mer, a nested latent Transformer to learn this hierarchical representation from human pose data in a fully self-supervised manner. A4Mer splits a 3D pose sequence into variable-length segments and represents each segment as a single latent token (Action Atoms). Through bottom-up representation learning, temporal patterns composed of these Action Atoms, which capture meaningful temporal spans of reusable, semantic segments of body movements, naturally emerge (Action Motifs). A4Mer achieves this with a unified pretext task of masked token prediction in their respective latent spaces. We also introduce Action Motif Dataset (AMD), a large-scale dataset of multi-view human behavior videos with full SMPL annotations. We introduce a novel use of cameras by mounting them on the feet to achieve their frame-wise annotations despite frequent and heavy body occlusions. Experimental results demonstrate the effectiveness of A4Mer for extracting meaningful Action Motifs, which significantly benefit human behavior modeling tasks including action recognition, motion prediction, and motion interpolation.

In this work, we propose a Multigrain-aware Semantic Prototype Scanning paradigm for pan-sharpening, built upon a high-order RWKV architecture and a tri-token prompting mechanism derived from semantic clustering. Specifically, our method contains three key components: 1) Multigrain-aware Semantic Prototype Scanning. Although RWKV offers an efficient linear-complexity alternative to Transformers, its conventional bidirectional raster scanning is still semantic-agnostic and prone to positional bias. To address this issue, we introduce a semantic-driven scanning strategy that leverages locality-sensitive hashing to group semantically related regions and construct multi-grain semantic prototypes, enabling context-aware token reordering and more coherent global interaction. 2) Tri-token Prompt Learning. We design a tri-token prompting mechanism consisting of a global token, cluster-derived prototype tokens, and a learnable register token. The global and prototype tokens provide complementary semantic priors for RWKV modeling, while the register token helps suppress noisy and artifact-prone intermediate representations. 3) Invertible Q-Shift. To counteract spatial details, we apply center difference convolution on the value pathway to inject high-frequency information, and introduce an invertible multi-scale Q-shift operation for efficient and lossless feature transformation without parameter-heavy receptive field expansion. Experimental results demonstrate the superiority of our method.

Full-body motion estimation from sparse VR observations is an inherently under-constrained problem, with only three 6-DoF trackers (HMD and controllers) available to infer a full skeletal pose. To address this ambiguity, we introduce a probabilistic framework that models joint orientations as distributions on SO(3) using the Matrix Fisher distribution. Instead of predicting a single deterministic pose, our network outputs a distribution for each joint, whose mode and concentration directly quantify prediction uncertainty on the rotation manifold. This enables likelihood-based training and principled uncertainty propagation. At the core of our model is a causal Transformer encoder that fuses sparse observations with motion history. We further propose region-wise tokens for the torso, arms, and legs, obtained via attention pooling over local joint features and semantic VR anchors. These tokens guide compact, per-region Fisher regression. To ensure kinematic coherence efficiently, we employ a limb refinement module, where each child joint's Fisher parameters are conditioned on its parent's distribution and the regional context, propagating pose and uncertainty hierarchically. Extensive experiments on standard sparse-VR benchmarks show that our approach achieves state-of-the-art performance, while providing well-calibrated joint-wise uncertainty.

Multi-camera 3D object detection (MC3D) has attracted increasing attention with the growing deployment of multi-sensor physical agents, such as robots and autonomous vehicles. However, MC3D models still struggle to generalize to unseen platforms with new multi-camera configurations. Current solutions simply employ a meta-camera for unified representation but lack comprehensive consideration. In this paper, we revisit this issue and identify that the devil lies in spatial prior discrepancies across source and target configurations, including different intrinsics, extrinsics, and array layouts. To address this, we propose CoIn3D, a generalizable MC3D framework that enables strong transferability from source configurations to unseen target ones. CoIn3D explicitly incorporates all identified spatial priors into both feature embedding and image observation through spatial-aware feature modulation (SFM) and camera-aware data augmentation (CDA), respectively. SFM enriches feature space by integrating four spatial representations, such as focal length, ground depth, ground gradient, and Plucker coordinate. CDA improves observation diversity under various configurations via a training-free dynamic novel-view image synthesis scheme. Extensive experiments demonstrate that CoIn3D achieves strong cross-configuration performance on landmark datasets such as NuScenes, Waymo, and Lyft, under three dominant MC3D paradigms represented by BEVDepth, BEVFormer, and PETR.

This paper addresses the challenge of training a single network to jointly perform multiple dense prediction tasks, such as segmentation and depth estimation, i.e., multi-task learning (MTL). Current approaches mainly capture cross-task relations in the 2D image space, often leading to unstructured features lacking 3D-awareness. We argue that 3D-awareness is vital for modeling cross-task correlations essential for comprehensive scene understanding. We propose to address this problem by integrating correlations across views, i.e., cost volume, as geometric consistency in the MTL network. Specifically, we introduce a lightweight Cross-view Module (CvM), shared across tasks, to exchange information across views and capture cross-view correlations, which are integrated with MTL encoder features for multi-task prediction. This module is architecture-agnostic and can be applied to both single- and multi-view data. Extensive results on NYUv2 and PASCAL-Context demonstrate that our method effectively injects geometric consistency into existing MTL methods to improve performance.