YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常

正在读取账号与研究记录…

全站更新概况

+2471新增论文

+2025其中 AI 相关

+163已有论文修订

+100新增 AI 导读

arXiv 最近完成扫描：2026-11-11 05:58 · 全站最近入库：2026-11-10 15:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-10 06:20 — 2026-11-11 06:20（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-11 05:58最近发现新增版本：2026-11-10 15:22库内论文最新更新时间：2026-11-10 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

20,643 已收录论文17,531 AI 相关5,643 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 4,042 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-11 05:57（北京时间）

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f4b4b958a98421d91a722209d6ce503fCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

TeFlow: Enabling Multi-frame Supervision for Self-Supervised Feed-forward Scene Flow Estimation

Zhang, Qingwen, Jiang, Chenhan, Zhu, Xiaomeng, Miao, Yunqi, Zhang, Yushan, Andersson, Olov, Jensfelt, Patric

原文摘要

Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusions. Multi-frame supervision has the potential to provide more stable guidance by incorporating motion cues from past frames, yet naive extensions of two-frame objectives are ineffective because point correspondences vary abruptly across frames, producing inconsistent signals.In the paper, we present TeFlow, enabling multi-frame supervision for feed-forward models by mining temporally consistent supervision. TeFlow introduces a temporal ensembling strategy that forms reliable supervisory signals by aggregating the most temporally consistent motion cues from a candidate pool built across multiple frames.Extensive evaluations demonstrate that TeFlow establishes a new state-of-the-art for self-supervised feed-forward methods, achieving performance gains of up to 33% on the challenging Argoverse 2 and nuScenes datasets. Our method performs on par with leading optimization-based methods, yet speeds up 150 times. The code is open-sourced at https://github.com/Kin-Zhang/TeFlow along with trained model weights.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f4bb121a56eaaa8f794a90ee3f991956CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation

Shen, Tingrui, Zhang, Yiheng, Tang, Chen, Ping, Chuan, Zhao, Zixing, Wan, Le, Wang, Yuwang, Wang, Ronggang 等 9 位作者

原文摘要

Autoregressive models can generate high-quality 3D meshes by sequentially producing vertices and faces, but their token-by-token decoding results in slow inference, limiting practical use in interactive and large-scale applications.We present FlashMesh, a fast and high-fidelity mesh generation framework that rethinks autoregressive decoding through a predict-correct-verify paradigm. The key insight is that mesh tokens exhibit strong structural and geometric correlations that enable confident multi-token speculation. FlashMesh leverages this by introducing a speculative decoding scheme tailored to the commonly used hourglass transformer architecture, enabling parallel prediction across face, point, and coordinate levels.Extensive experiments show that FlashMesh achieves up to a 2xspeedup over standard autoregressive models while also improving generation fidelity. Our results demonstrate that structural priors in mesh data can be systematically harnessed to accelerate and enhance autoregressive generation.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f4c0f29739726ae947eb379fa807b148CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Coverage Optimization for Camera View Selection

Chen, Timothy, Dai, Adam, Adang, Maximilian, Gao, Grace, Schwager, Mac

原文摘要

What makes a good viewpoint? The quality of the data used to learn 3D reconstructions is crucial for enabling efficient and accurate scene modeling. We study the active view selection problem and develop a principled analysis that yields a simple and interpretable criterion for selecting informative camera poses. Our key insight is that informative views can be obtained by minimizing a tractable approximation of the Fisher Information Gain, which reduces to favoring viewpoints that cover geometry that has been insufficiently observed by past cameras. This leads to a lightweight coverage-based view selection metric that avoids expensive transmittance estimation and is robust to noise and training dynamics. We call this metric CONVERGE (Coverage Optimized Novel Viewset Estimation for Reconstructing Geometry Efficiently). We integrate our method into the Nerfstudio framework and evaluate it on real datasets within fixed and embodied data acquisition scenarios. Across multiple datasets and radiance-field baselines, our method consistently improves reconstruction quality compared to state-of-the-art active view selection methods.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f4e30629dd27b96f415d2a0db9266f5aCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

SafeLogo: Turning Your Logos into Jailbreak Shields via Micro-Regional Adversarial Training

Duan, Zhiyi, Zhang, Xiaoyue, Man, Tianxing

原文摘要

Recent Vision-Language Models (VLMs) have become increasingly susceptible to jailbreak attacks, where adversarial prompts exploit subtle manipulation to circumvent safety alignment.The diversity and adaptability of such jailbreakers necessitate a defense mechanism with strong generalization capability.However, fine-tuning large-scale VLMs is computationally expensive, and introducing excessive visual or textual defense prompts is impractical for preserving image realism and model usability.We propose SafeLogo, which tunes a logo-sized visual prompt into a universal shield against diverse jailbreak attacks through micro-regional adversarial training.We are the first to integrate min-max adversarial optimization into visual defense prompt generation.Specifically, in the outer loop, SafeLogo injects compact, bounded perturbations into extremely small image regions (\leq 2% pixel coverage), effectively preserving both visual fidelity and semantic consistency.Meanwhile, overcoming the limitations of prior defenses constrained to a single attack direction or fixed benign supervision, the inner loop dynamically generates and selects the strongest one from a variety of jailbreakers.Extensive experiments on LLaVA-1.5-13B,MiniGPT-4, and Qwen3-VL show that SafeLogo markedly lowers jailbreak success rates on MM-SafetyBench, VLGuard, and FigStep, while preserving benign performance on MM-Vet and MME.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f4ed08865a85a4b4930f3e75919718b0CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Video-as-Answer: Predict and Generate Next Video Event with Joint-GRPO

Cheng, Junhao, Hou, Liang, Tao, Xin, Liao, Jing

原文摘要

While language models have become impactful in many real-world applications, video generation remains largely confined to entertainment. Motivated by video's inherent capacity to demonstrate physical-world information that is difficult to convey through language alone (e.g., imagine teaching someone to tie a tie using only text), we identify an underutilized opportunity to extend video as a new answer modality for Next-Event Prediction (NEP), formalized as Video-Next-Event Prediction (VNEP). While the established NEP task takes a video with a procedural or predictive question as input to predict the next event in text, VNEP requires dynamic video responses. This shift from telling to showing unlocks more intuitive and customized answers for procedural learning and creative exploration. However, this task remains challenging for existing models, as it demands an understanding of multimodal input, instruction-conditioned reasoning, and the generation of video with visual and semantic consistency. To address this, we introduce VANS, a model that leverages reinforcement learning to align a Vision-Language Model (VLM) with a Video Diffusion Model (VDM) for VNEP. The core of VANS is our proposed Joint-GRPO that orchestrates the VLM and VDM to function as a unit. Driven by a shared reward on their respective output, it optimizes the VLM to produce captions that are both accurate and friendly to visualize, while guiding the VDM to generate videos that are faithful to these captions and the input visual context. To enable this learning, we craft VANS-Data-100K, a dedicated dataset for the VNEP task. Experiments on procedural and predictive benchmarks demonstrate that VANS achieves state-of-the-art performance in both video event prediction and visualization.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f5039fa1e0b042d669b4b0fdcef264dbCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

PointCSP: Cross-Sample Semantic Propagation and Stability Preservation in Self-Supervised Point Cloud Learning

Yu, Xinxing, Liu, Ajian, Qiang, Sunyuan, Ma, Hui, Yang, Liying, Wang, Yuzhong, Rao, Zhi, Liang, Yanyan

原文摘要

Scene-level point cloud self-supervised learning (PC-SSL) has demonstrated potential in enhancing the generalization capability of 3D vision models. Despite the advances in the field through existing methods, the sample-independent modeling paradigm still poses significant limitations in terms of maintaining consistent semantic representations across scenes. This challenge hinders the construction of a unified and transferable semantic space. To address this issue, we propose a PC-SSL framework based on cross-sample semantic propagation (CSP), in which samples within a batch are serialized into continuous input and processed by a state-space model to enable semantic state propagation. This mechanism explicitly models the dynamic dependencies across samples in the state space, allowing the network to establish cross-sample semantic consistency in the latent space and achieve global semantic alignment. Since serialization-based pretraining requires batch-level input organization, we further introduce an asymmetric semantic preservation distillation (SPD) during finetuning to achieve structural alignment of semantic transfer and eliminate inconsistencies caused by batch dependency. The proposed SPD ensures stable transfer of pretrained semantics through a heterogeneous input mechanism and a semantic feature alignment constraint. This enables the model to maintain structured semantic consistency and robustness under single-scene testing conditions. Extensive experiments on multiple benchmark datasets demonstrate that our method consistently outperforms state-of-the-art methods in both performance and semantic consistency.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f50a4be0e84273c794bd1591080a580aCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Pip-Stereo: Progressive Iterations Pruner for Iterative Optimization based Stereo Matching

Zheng, Jintu, Liu, Qizhe, Xu, Huangxin, Chen, Zhuojie

原文摘要

While iterative stereo matching achieves high accuracy, its dependence on Recurrent Neural Networks (RNN) hinders edge deployment, a challenge underexplored in existing researches. We analyze iterative refinement and reveal that disparity updates are spatially sparse and temporally redundant. First, we introduce a progressive iteration pruning strategy that suppresses redundant update steps, effectively collapsing the recursive computation into a near-single-pass inference. Second, we propose a collaborative monocular prior transfer framework that implicitly embeds depth priors without requiring a dedicated monocular encoder, thereby eliminating its associated computational burden. Third, we develop FlashGRU, a hardware-aware RNN operator leveraging structured sparsity and I/O-conscious design, achieving a 7.28xspeedup, 76.6% memory peak reduction and 80.9% global memory requests reduction over natvie ConvGRUs under 2K resolution. Our PipStereo enables real-time, high-fidelity stereo matching on edge hardware: it processes 320x640 frames in just 75ms on an NVIDIA Jetson Orin NX (FP16) and 19ms on RTX 4090, matching the accuracy of large iterative based models, and our generalization ability and accuracy far exceeds that of existing real-time methods.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f513c78d4249883dbb6ed442d9dbd211CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

U-Mind: A Unified Framework for Real-Time Multimodal Interaction with Audiovisual Generation

Deng, Xiang, Gao, Feng, Zhang, Yong, Pang, Youxin, Xiaoming, Xu, Kang, Zhuoliang, Wei, Xiaoming, Liu, Yebin

原文摘要

Full-stack multimodal interaction in real-time is a central goal in building intelligent embodied agents capable of natural, dynamic communication. However, existing systems are either limited to unimodal generation or suffer from degraded reasoning and poor cross-modal alignment, preventing coherent and perceptually grounded interactions. In this work, we introduce U-Mind, the first unified system for high-intelligence multimodal dialogue that supports real-time generation and jointly models language, speech, motion, and video synthesis within a single interactive loop. At its core, U-Mind implements a Unified Alignment and Reasoning Framework that addresses two key challenges: enhancing cross-modal synchronization via a segment-wise alignment strategy, and preserving reasoning abilities through Rehearsal-Driven Learning. During inference, U-Mind adopts a text-first decoding pipeline that performs internal chain-of-thought planning followed by temporally synchronized generation across modalities. To close the loop, we implement a real-time video rendering framework conditioned on pose and speech, enabling expressive and synchronized visual feedback. Extensive experiments demonstrate that U-Mind achieves state-of-the-art performance on a range of multimodal interaction tasks, including question answering, instruction following, and motion generation, paving the way toward intelligent, immersive conversational agents.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f51667cf0963bdebe28381d71762db7eCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Cross-Hand Latent Representation for Vision-Language-Action Models

Jiang, Guangqi, Liang, Yutong, Ye, Jianglong, Huang, Jia-Yang, Jing, Changwei, Duan, Rocky, Abbeel, Pieter, Wang, Xiaolong 等 9 位作者

原文摘要

Dexterous manipulation is essential for real-world robot autonomy, mirroring the central role of human hand coordination in daily activity. Humans rely on rich multimodal perception--vision, sound, and language-guided intent--to perform dexterous actions, motivating vision-based, language-conditioned manipulation systems for robots. However, training reliable vision-language-action (VLA) models for dexterous manipulation requires large-scale demonstrations across many robotic hands. In addition, as new dexterous embodiments appear rapidly, collecting data for each becomes costly and impractical, creating a need for scalable cross-embodiment learning. We introduce \ourmethod, a vision-language-action framework integrated with a unified latent action space shared across diverse dexterous hands. This embodiment-invariant latent space is directly pluggable into standard VLA architectures, enabling seamless cross-embodiment training and efficient reuse of both existing and newly collected data. Experimental results demonstrate that \ourmethod consistently outperforms baseline VLA models operating in raw joint spaces, establishing it as an effective solution for scalable cross-embodiment dexterous manipulation.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f549389a68c9a5b51a0ee568520b11fdCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting

Chen, Hao, Han, Tao, Zhang, Jie, Guo, Song, Bai, Lei

原文摘要

To gain finer regional forecasts, many works have explored the regional integration from the global atmosphere, e.g., by solving boundary equations in physics-based methods or cropping regions from global forecasts in data-driven methods. However, the effectiveness of these methods is often constrained by static and imprecise regional boundaries, resulting in poor generalization ability. To address this issue, we propose Spatial-Temporal Weather Forecasting (STCast), a novel AI-driven framework for adaptive regional boundary optimization and dynamic monthly forecast allocation. Specifically, our approach employs a Spatial-Aligned Attention (SAA) mechanism, which aligns global and regional spatial distributions to initialize boundaries and adaptively refines them based on attention-derived alignment patterns. Furthermore, we design a Temporal Mixture-of-Experts (TMoE) module, where atmospheric variables from distinct months are dynamically routed to specialized experts using a discrete Gaussian distribution, enhancing the model's ability to capture temporal patterns. Beyond global and regional forecasting, STCast is evaluated on extreme event prediction and ensemble forecasting. Experimental results demonstrate consistent superiority over other methods across all four tasks. Code: https://github.com/chenhao-zju/STCast

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f54ebabbae6a4ee85b74fc9ee84762b3CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

SemanticVLA: Towards Semantic Reasoning over Action Memorization via Synergistic Explicit Trace and Latent Action Planning

Ni, Fei, Chen, Zhuo, Yuan, Yifu, Dong, Zibin, Yao, Xianze, Luo, Shan, Hao, Jianye, Deng, Jiankang 等 9 位作者

原文摘要

Vision-Language-Action (VLA) models have emerged as a promising paradigm where pretrained Vision-Language Models (VLMs) serve as System 2 for high-level reasoning, connected to action experts as System 1 for low-level motor control.However, current works fail to genuinely leverage VLM capabilities: VLMs produce latent embeddings that lack semantic interpretability, providing ambiguous and unstable guidance to downstream policies, while solely action supervision further causes VLMs to degenerate into parameter-heavy fusion encoders that memorize action patterns rather than perform generalized reasoning.To bridge this gap, we introduce SemanticVLA, which leverages VLM reasoning through synergistic dual-path design. Explicit trace reasoning generates interpretable spatial waypoints as textual coordinate sequences through the VLM's native language interface, directly reusing its pretrained spatial grounding to provide a thinking process for task planning. Latent action tokens complement trace reasoning by learning compact visuomotor primitives grounded in visual observations, providing more fine-grained action representations beyond pure coordinate prediction. This synergy enables trace reasoning to leverage VLM's multimodal understanding for refining latent token prediction, while latent tokens provide stable and grounded guidance that compensates for trace's numerical sensitivity.SemanticVLA achieves 97.0% average success rate on LIBERO and 65.1% on SimplerEnv WidowX, substantially outperforming strong baselines. More importantly, SemanticVLA maintains significantly more stable performance under instruction rephrasing in both simulation suites, and demonstrates strong advantages on real-world long-horizon and reasoning-intensive tasks.By bridging VLM reasoning and action expert through semantically explicit trace and visually grounded latent action tokens, our approach enables genuine reasoning rather than action memorization.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f57490d03332e898212365e3e23891c0CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Physically-Grounded Turbulence Mitigation with Frame-Shared Degradation Parameters

Xie, Dongxin, Huang, Yan, Xu, Yong, Ji, Hui

原文摘要

Atmospheric turbulence causes spatially varying distortion and blur in long-range imaging, making restoration highly challenging in real-world applications. Supervised methods rely on synthetic training data, whose simulated degradation often cannot faithfully reflect real turbulence. Existing unsupervised methods usually estimate degradation parameters for each frame independently, without exploiting the shared correlations among frames from the same scene. We propose TMFS, an optimization-based and physics-grounded method for unsupervised turbulence restoration. TMFS is based on a physically motivated tilt-then-blur degradation model and represents frame degradations through a shared turbulence structure. By decomposing the distortion and blur of each frame into a scene-shared correlation function and per-frame noise maps, TMFS enables cross-frame information sharing and alleviates the ill-posedness of framewise estimation. Experiments on synthetic and real datasets demonstrate the effectiveness of TMFS and its strong generalization to real turbulence.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f593a86012341b8f13449fc93b9b6b91CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Global-Graph Guided and Local-Graph Weighted Contrastive Learning for Unified Clustering on Incomplete and Noise Multi-View Data

He, Hongqing, Xu, Jie, Yang, Wenyuan, Zhu, Yonghua, Wen, Guoqiu, Zhu, Xiaofeng

原文摘要

Recently, contrastive learning (CL) plays an important role in exploring complementary information for multi-view clustering (MVC) and has attracted increasing attention. Nevertheless, real-world multi-view data suffer from data incompleteness or noise, resulting in rare-paired samples or mis-paired samples which significantly challenge the effectiveness of CL-based MVC. That is, rare-paired issue prevents MVC from extracting sufficient multi-view complementary information, and mis-paired issue causes contrastive learning to optimize the model in the wrong direction. To address these issues, we propose a unified CL-based MVC framework for enhancing clustering effectiveness on incomplete and noise multi-view data. First, to mitigate the rare-paired issue, we design a global-graph guided contrastive learning, where all view samples construct a global-view affinity graph to form new sample pairs for fully exploring complementary information. Second, to overcome the mis-paired issue, we propose a local-graph weighted contrastive learning, which leverages local neighbors to generate pair-wise weights to adaptively strength or weaken the pair-wise contrastive learning. Our method is imputation-free and can be integrated into a unified global-local graph-guided contrastive learning framework. Extensive experiments on both incomplete and noise settings of multi-view data demonstrate that our method achieves superior performance compared with state-of-the-art approaches.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f5947cbbae8d4e3ac1b301fe7a7c6f48CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Multi-Scale Local Speculative Decoding for Image Generation

Peruzzo, Elia, Sautière, Guillaume, Habibian, Amirhossein

原文摘要

Autoregressive (AR) models have achieved remarkable success in image synthesis, yet their sequential nature imposes significant latency constraints. Speculative Decoding offers a promising avenue for acceleration, but existing approaches are limited by token-level ambiguity and lack of spatial awareness. In this work, we introduce Multi-Scale Local Speculative Decoding (MuLo-SD), a novel framework that combines multi-resolution drafting with spatially informed verification to accelerate AR image generation. Our method leverages a low-resolution drafter paired with an up-sampling step to propose candidate image tokens, which are then verified in parallel by a high-resolution target model. Crucially, we incorporate a local rejection and resampling mechanism, enabling efficient correction of draft errors by focusing on spatial neighborhoods rather than raster-scan resampling after the first rejection. When integrated with parallel decoding resampling, \methodname achieves substantial speedups -- up to 5x -- outperforming both speculative decoding and parallel decoding baselines in terms of acceleration, while maintaining comparable semantic alignment and perceptual quality. These results are validated using GenEval, DPG-Bench, and FID/HPSv2 on the MS-COCO 5k validation split. Extensive ablations highlight the impact of up-sampling design, probability pooling, and local rejection and resampling with neighborhood expansion. Our approach sets a new state-of-the-art in speculative decoding for image synthesis, bridging the gap between efficiency and fidelity.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f5aa31e5ef4368c64a7ea3b7d02fc363CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Mobile-VTON: High-Fidelity On-Device Virtual Try-On

Wan, Zhenchen, Chen, Ce, Lin, Runqi, Huang, Jiaxin, Chen, Tianxi, Xu, Yanwu, Liu, Tongliang, Gong, Mingming

原文摘要

Virtual try-on (VTON) has recently achieved impressive visual fidelity, but most existing systems require uploading personal photos to cloud-based GPUs, raising privacy concerns and limiting on-device deployment. To address this, we present Mobile-VTON, a high-quality, privacy-preserving framework that enables fully offline virtual try-on on commodity mobile devices using only a single user image and a garment image. Mobile-VTON introduces a modular TeacherNet--GarmentNet--TryonNet (TGT) architecture that integrates knowledge distillation, garment-conditioned generation, and garment alignment into a unified pipeline optimized for on-device efficiency. Within this framework, we propose a Feature-Guided Adversarial (FGA) Distillation strategy that combines teacher supervision with adversarial learning to better match real-world image distributions. GarmentNet is trained with a trajectory-consistency loss to preserve garment semantics across diffusion steps, while TryonNet uses latent concatenation and lightweight cross-modal conditioning to enable robust garment-to-person alignment without large-scale pretraining. By combining these components, Mobile-VTON achieves high-fidelity generation with low computational overhead. Experiments on VITON-HD and DressCode at 1024 x 768 show that it matches or outperforms strong server-based baselines while running entirely offline. These results demonstrate that high-quality VTON is not only feasible but also practical on-device, offering a secure solution for real-world applications.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f5abc6e2d0f2b1142932aefcba2f76c7CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Vista4D: Video Reshooting with 4D Point Clouds

Lin, Kuan Heng, Liu, Zhizheng, Salamanca, Pablo, Kant, Yash, Burgert, Ryan, Xu, Yuancheng, Namekata, Koichi, Zhao, Yiwei 等 12 位作者

原文摘要

We present **Vista4D**, a robust and flexible video reshooting framework that grounds the input video and target cameras in a 4D point cloud. Specifically, given an input video, our method re-synthesizes the scene with the same dynamics from a different camera trajectory and viewpoint. Existing video reshooting methods often struggle with depth estimation artifacts of real-world dynamic videos, while also failing to preserve content appearance and maintain precise camera control for challenging new trajectories. We build a 4D-grounded point cloud representation with static pixel segmentation and 4D reconstruction to explicitly preserve seen content and provide rich camera signals, and we train with reconstructed multiview dynamic data for robustness against point cloud artifacts during real-world inference. Our results demonstrate improved 4D consistency, camera control, and visual quality compared to state-of-the-art baselines under a variety of videos and camera paths. Moreover, our method generalizes to real-world applications such as dynamic scene expansion and 4D scene recomposition. Results are best viewed as videos in the Supplement.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f5b5b17413e68754ca97903695462b9eCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation

Jiang, Chenhan, Chen, Yu, Zhang, Qingwen, Song, Jifei, Xu, Songcen, Yeung, Dit-Yan, Deng, Jiankang

原文摘要

The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are typically sparse and discrete. Conversely, synthetic data scales but suffers from a domain gap and often lacks realistic semantics. We introduce \change FreeScale , a novel framework that leverages the power of scene reconstruction to transform limited real-world image sequences into a scalable source of high-quality training data. Our key insight is that an imperfect reconstructed scene serves as a rich geometric proxy, but naively sampling from it amplifies artifacts. To this end, we propose a certainty-aware free-view sampling strategy \change identifying novel viewpoints that are both semantically meaningful and minimally affected by reconstruction errors. We demonstrate \change FreeScale 's effectiveness by scaling up the training of feedforward NVS models, achieving a \change notable gain of 2.7 dB in PSNR on challenging out-of-distribution benchmarks. Furthermore, we show that the generated data can actively enhance per-scene 3D Gaussian Splatting optimization, leading to consistent improvements across multiple datasets. Our work provides a practical and powerful data generation engine to overcome a fundamental bottleneck in 3D vision. \change Project page: https://mvp-ai-lab.github.io/FreeScale .

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f5c0f2b203f95712faa716a2f00985f3CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

MajutsuCity: Language-driven Aesthetic-adaptive City Generation with Controllable 3D Assets and Layouts

Huang, Zilong, He, Jun, Huang, Xiaobin, Xiong, Ziyi, Luo, Yang, Ye, Junyan, Li, Weijia, Chen, Yiping 等 9 位作者

原文摘要

Generating realistic 3D cities is fundamental to world models, virtual reality, and game development, where an ideal urban scene must satisfy both stylistic diversity, fine-grained, and controllability. However, existing methods struggle to balance the creative flexibility offered by text-based generation with the object-level editability enabled by explicit structural representations. We introduce MajutsuCity, a natural language-driven and aesthetically adaptive framework for synthesizing structurally consistent and stylistically diverse 3D urban scenes. MajutsuCity represents a city as a composition of controllable layouts, assets, and materials, and operates through a four-stage pipeline. To extend controllability beyond initial generation, we further integrate MajutsuAgent, an interactive language-grounded editing agent that supports five object-level operations. To support photorealistic and customizable scene synthesis, we also construct MajutsuDataset, a high-quality multimodal dataset containing 2D semantic layouts and height maps, diverse 3D building assets, and curated PBR materials and skyboxes, each accompanied by detailed annotations. Meanwhile, we develop a practical set of evaluation metrics, covering key dimensions such as structural consistency, scene complexity, material fidelity, and lighting atmosphere. Extensive experiments demonstrate MajutsuCity reduces layout FID by 83.7% compared with CityDreamer and by 20.1% over CityCraft. Our method ranks first across all AQS and RDR scores, outperforming existing methods by a clear margin. These results confirm MajutsuCity as a new state-of-the-art in geometric fidelity, stylistic adaptability, and semantic controllability for 3D city generation. We expect our framework can inspire new avenues of research in 3D city generation. Our project page: https://longhz140516.github.io/MajutsuCity/

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f5c5b76925bae2d1591e2ebe6bd82c85CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects

Iliash, Denys, Liu, Jiayi, Fokin, Egor, Wu, Qirui, Amiri, Ali Mahdavi, Savva, Manolis, Chang, Angel X.

原文摘要

We present Artiverse, a diverse and physically grounded dataset of high-quality articulated 3D objects designed for realistic functional modeling and simulation. Artiverse contains 5.4K human-authored objects across a broad range of 88 categories, aggregated from multiple 3D static repositories. Objects are annotated with functional parts, interior structures, realistic kinematic relationships including multi-DoF joints, and physical attributes such as metric scale, material, and mass. We develop a semi-automated annotation pipeline that combines few-shot segmentation, geometric reasoning, and multi-stage human verification to achieve high-quality and efficient annotation, reducing manual annotation time by over 30%. We demonstrate the value of Artiverse on tasks of part mobility analysis, articulated object generation, and physics-based interaction. Artiverse provides a data resource to advance functional understanding for articulated objects.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f5ddda9632a1b074306aab3ded12b03fCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Shoe Style-Invariant and Ground-Aware Learning for Dense Foot Contact Estimation

Jung, Daniel Sungho, Lee, Kyoung Mu

原文摘要

Foot contact plays a critical role in human interaction with the world, and thus exploring foot contact can advance our understanding of human movement and physical interaction. Despite its importance, existing methods often approximate foot contact using a zero-velocity constraint and focus on joint-level contact, failing to capture the detailed interaction between the foot and the world. Dense estimation of foot contact is crucial for accurately modeling this interaction, yet predicting dense foot contact from a single RGB image remains largely underexplored. There are two main challenges for learning dense foot contact estimation. First, shoes exhibit highly diverse appearances, making it difficult for models to generalize across different styles. Second, ground often has a monotonous appearance, making it difficult to extract informative features. To tackle these issues, we present a FEet COntact estimation (FECO) framework that learns dense foot contact with shoe style-invariant and ground-aware learning. To overcome the challenge of shoe appearance diversity, our approach incorporates shoe style adversarial training that enforces shoe style-invariant features for contact estimation. To effectively utilize ground information, we introduce a ground feature extractor that captures ground properties based on spatial context. As a result, our proposed method achieves robust foot contact estimation regardless of shoe appearance and effectively leverages ground information. The codes are available at https://github.com/dqj5182/FECO_RELEASE.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f5e0bdcb01aee76603dd0119f61d9801CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching

Zheng, Caleb, Shlizerman, Eli

原文摘要

Diffusion models achieve remarkable performance across diverse generative tasks in computer vision, but their high computational cost remains a major barrier to deployment. Model pruning offers a promising way to reduce inference cost and enable lightweight models. However, pruning leads to quality drop due to reduced capacity. A key limitation of existing pruning approaches is that pruned models are finetuned using the same objective as the dense model (denoising score matching). Since the dense model is accessible during finetuning, it warrants a more effective approach for knowledge transfer from the dense to the pruned model. Motivated by this, we propose 2ndMatch(2ndM), a general-purpose finetuning framework that introduces a 2nd-order Jacobian (J^ \top J) Matching loss inspired by Finite-Time Lyapunov Exponents. 2ndM teaches the pruned model to mimic the sensitivity of the dense teacher, i.e., how to respond to small perturbations over time, through scalable random projections. The framework is architecture-agnostic and applies to both U-Net- and Transformer-based diffusion models. Experiments on CIFAR-10, CelebA, LSUN, ImageNet, and MSCOCO demonstrate that 2ndM reduces the performance gap between pruned and dense models, substantially improving output quality.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f602bbf9820ff01463149ab10902cbf3CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models

Xia, Zaishuo, Lu, Yukuan, Li, Xinyi, Xu, Yifan, Chen, Yubei

原文摘要

A world model is an internal model that simulates how the world evolves. Given past observations and actions, it predicts the future physical state of both the embodied agent and its environment. Accurate world models are essential for enabling agents to think, plan, and reason effectively in complex, dynamic settings. However, existing world models often focus on random generation of open worlds, but neglect the need for high-fidelity modeling of deterministic scenarios (such as fixed-map mazes and static space robot navigation). In this work, we take a step toward building a truly accurate world model by addressing a fundamental yet open problem: constructing a model that can fully clone a deterministic world. 1) Through diagnostic experiment, we quantitatively demonstrate that high-fidelity cloning is feasible and the primary bottleneck for long-horizon fidelity is the geometric structure of the latent representation, not the dynamics model itself. 2) Building on this insight, we show that applying temporal contrastive learning principle as a geometric regularization can effectively curate a latent space that better reflects the underlying physical state manifold, demonstrating that contrastive constraints can serve as a powerful inductive bias for stable world modeling; we call this approach Geometrically-Regularized World Models (GRWM). At its core is a lightweight geometric regularization module that can be seamlessly integrated into standard autoencoders, reshaping their latent space to provide a stable foundation for effective dynamics modeling. By focusing on representation quality, GRWM offers a simple yet powerful pipeline for improving world model fidelity. Code is available at https://github.com/XiaFire/Clone_Deterministic_Environment.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f6368357bbaada5d7c62960052ce627fCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

GaussianMatch: Semi-Supervised Regression with Pseudo-Label Filtering via Multi-View Gaussian Consistency

Wang, Yin, Lu, Hao, Wang, Zixuan, Qin, Zhen, Kuang, Li, Zhou, Mengchu, Deng, Shuiguang

原文摘要

Semi-Supervised Regression (SSR) is essential in domains like sentiment analysis and healthcare where labeled data is limited but unlabeled data is plentiful. Despite its practical importance, SSR remains underexplored due to the lack of effective pseudo-labeling strategies for continuous outputs. Unlike classification, regression lacks inherent confidence measures, making it harder to filter and trust pseudo-labels. This limitation permits low-quality pseudo-labels to propagate during training without proper validation, significantly amplifying prediction errors in SSR frameworks. In this work, we propose GaussianMatch, a novel SSR framework enabling high-quality pseudo-label filtering, which selects reliable pseudo-labels through multi-view prediction consistency under feature-space smoothness assumptions. It has introduces two key innovations: 1) Gaussian Consistency Filter (GCF) that quantifies prediction consistency across weakly augmented views through Gaussian similarity scoring, retaining pseudo-labels only when all predictions fall within a confidence interval; 2) Adaptive Gaussian Standard Deviation Smoothing (AGDS) that enhances GCF's robustness through a Bayesian-regularized curriculum that phases confidence intervals from warm-up conservative bounds to progressively tightened thresholds. The use of AGDS ensures stable and reliable pseudo-label filtering throughout training. Extensive experiments demonstrate that GaussianMatch performs strongly across varying data conditions, showing notable robustness under extreme label scarcity. For instance, it outperforms the state of the art on UTKFace (30 labels), reducing error by 15.36% and improving the Coefficient of Determination by 50.21%. Our code is available at https://github.com/pywin/GaussianMatch.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f63abd72f6d89ea421dd5d23bc6e0356CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

CICA: Coupling Confidence-Aware Pretraining with Confidence-Informed Attention for Robust Multimodal Sentiment Analysis

Jiang, Haoyu, Chen, Xiaoliang, Miao, Duoqian, Qin, Xiaolin, Li, Xianyong, Du, Yajun

原文摘要

Multimodal sentiment analysis requires integrating language, visual, and acoustic cues, yet these modalities are often noisy, incomplete, or contradictory, making fusion unreliable. Most existing methods assume uniformly trustworthy modalities and thus degrade when signals conflict. To address this, we propose CICA, a framework that couples Confidence-Aware Pretraining with Confidence-Informed Attention. In pretraining, each modality encoder learns to estimate the reliability of its own representation, producing both embeddings and confidence scores. These scores then guide a confidence-informed attention mechanism, which strengthens contributions from reliable modalities while suppressing noisy or conflicting ones, enabling adaptive fusion under varying signal conditions. CICA achieves state-of-the-art performance across four major benchmarks on MOSI, MOSEI, CH-SIMS, and CH-SIMSv2. It achieves MAE 0.630 and Corr 0.855 on MOSI, and MAE 0.489 and Corr 0.856 on MOSEI, significantly surpassing prior methods. Consistent improvements are also observed across Acc-7, Acc-2, and F1 metrics. Under noisy and missing-modality conditions, CICA maintains significantly more stable performance, indicating improved robustness and interpretability.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f663cff2ce13c5aa2805d572ffd3be41CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

MagicFuse: Single Image Fusion for Visual and Semantic Reinforcement

Zhang, Hao, Zha, Yanping, Li, Zizhuo, Gong, Meiqi, Ma, Jiayi

原文摘要

This paper focuses on a highly practical scenario: how to continue benefiting from the advantages of multi-modal image fusion under harsh conditions when only visible imaging sensors are available. To achieve this goal, we propose a novel concept of single image fusion, which extends conventional data-level fusion to the knowledge level. Specifically, we develop MagicFuse, a novel single image fusion framework capable of deriving a comprehensive cross-spectral scene representation from a single low-quality visible image. MagicFuse first introduces an intra-spectral knowledge reinforcement branch and a cross-spectral knowledge generation branch based on the diffusion models. They mine scene information obscured in the visible spectrum and learn thermal radiation distribution patterns transferred to the infrared spectrum, respectively. Building on them, we design a multi-domain knowledge fusion branch that integrates the probabilistic noise from the diffusion streams of these two branches, from which a cross-spectral scene representation can be obtained through successive sampling. Then, we impose both visual and semantic constraints to ensure that this scene representation can satisfy human observation while supporting downstream semantic decision-making. Extensive experiments show that our MagicFuse achieves visual and semantic representation performance comparable to or even better than state-of-the-art fusion methods with multi-modal inputs, despite relying solely on a single degraded visible image. The code is publicly available at https://github.com/zhayanping/MagicFuse.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f664d37dbfa077313162512749741bc3CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

3D-LATTE: Latent Space 3D Editing from Textual Instructions

Parelli, Maria, Oechsle, Michael, Niemeyer, Michael, Tombari, Federico, Geiger, Andreas

原文摘要

Despite the recent success of multi-view diffusion models for text/image-based 3D asset generation, instruction-based editing of 3D assets lacks surprisingly far behind the quality of generation models. The main reason is that recent approaches using 2D priors suffer from view-inconsistent editing signals. Going beyond 2D prior distillation methods and multi-view editing strategies, we propose a novel editing method that operates within the latent space of a native 3D diffusion model, allowing us to directly manipulate 3D geometry. We guide the edit synthesis by blending 3D attention maps from the generation with the source object. Coupled with geometry-aware regularization guidance, a spectral modulation strategy in the Fourier domain and a refinement step for 3D enhancement, our method outperforms previous 3D editing methods enabling high-fidelity and precise edits across a wide range of shapes and semantic manipulations. Our project webpage is https://mparelli.github.io/3d-latte.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f66c78ec67ffd09ce292a27cf14cd843CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

DiffuView: Multi-View Diffusion Pretraining for 3D Aware Robotic Manipulation

Zhang, Kaizhao, Niu, Tian, Liu, Tianyu, Guo, Chenen, Xu, Zijun, Hu, Qingda, Ding, Wenchao

原文摘要

Robotic manipulation from visual observations remains challenging due to the lack of 3D consistent representations that can generalize across diverse viewpoints and sensor configurations. Existing approaches often rely on masked autoencoders or neural scene representations, which fail to capture cross view correspondences. Crucially, while multi-view diffusion models have recently shown tremendous success in 3D aware generative synthesis, their powerful representations offer a promising direction for achieving viewpoint robust visuomotor control. In this paper, we introduce DiffuView, a novel framework that learns unified 3D aware representations through multi-view diffusion pretraining and deploys them for imitation learning. Specifically, DiffuView models the conditional generation of target views given source observations within a diffusion framework, enabling the network to implicitly recover scene geometry and enforce view consistency. The pretrained diffusion network is then utilized as a powerful visual backbone for an action policy, allowing robust control under varying viewpoints and visual conditions. We evaluate DiffuView on two challenging benchmarks, MetaWorld and Libero. Extensive experiments in both simulation and realworld scenarios demonstrate that DiffuView achieves superior generalization, improving success rates under viewpoint shifts by nearly 20% compared with existing methods.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f68c3858d506618853639f206f2f301cCVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

4DP-QA: Scalable QA for 4D Perception in Vision Language Models

Cho, Seokju, Badki, Abhishek, Su, Hang, Jiang, Jindong, Zeng, Ziyao, Kim, Seungryong, Liu, Sifei, Gallo, Orazio

原文摘要

Despite recent advances, Vision Language Models (VLMs) still struggle to grasp the dynamics of the world. We note that the ability to reason about a 4D scene, challenging in itself, is further complicated by two factors. First, VLMs observe motion indirectly via its projection onto 2D images. Second, existing datasets fail to disentangle object and camera motion. To address these challenges, we present a QA generation pipeline that focuses on motion-related scene understanding. We take particular care of the entanglement of camera and object motion by casting tracking in both the traditional way and in a novel, fixed reference system, dubbed True-Motion Tracking, which provides an intuitive description of motion. From this pipeline, we generate a large-scale training dataset of 400K samples, 4DP-QA (4D Perception QA), and a 2.2K-sample benchmark, 4DP-QA-Bench. Training existing models on our dataset yields performance improvements on an external benchmark, validating the effectiveness of our method.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f6a28c9782927238804a6b09fa6d8c44CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Seeing through Light and Darkness: Sensor-Physics Grounded Deblurring HDR NeRF from Single-Exposure Images and Events

Qi, Yunshan, Zhu, Lin, Bao, Nan, Zhao, Yifan, Li, Jia

原文摘要

Novel view synthesis from low dynamic range (LDR) blurry images, which are common in the wild, struggles to recover high dynamic range (HDR) and sharp 3D representations in extreme lighting conditions. Although existing methods employ event data to address this issue, they ignore the sensor-physics mismatches between the camera output and physical world radiance, resulting in suboptimal HDR and deblurring results. To cope with this problem, we propose a unified sensor-physics grounded NeRF framework for sharp HDR novel view synthesis from single-exposure blurry LDR images and corresponding events. We employ NeRF to directly represent the actual radiance of the 3D scene in the HDR domain and model raw HDR scene rays hitting the sensor pixels as in the physical world. A 2D pixel-wise RGB CRF model is introduced to align the NeRF rendered pixel values with the sensor-recorded LDR pixel values of the input images. A novel event CRF model is also designed to bridge the gap between physical scene dynamics and event sensor output. The two models are jointly optimized with the NeRF network, leveraging the spatial and temporal dynamic information in events to enhance the sharp HDR 3D representation learning. Experiments on the collected and public datasets demonstrate that our method achieves state-of-the-art HDR and deblurring novel view synthesis results with single-exposure blurry LDR images and corresponding events. Our code and datasets are publicly available at https://github.com/iCVTEAM/See-NeRF.

cs.CV

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗

首次观测 · 记录 #1CVF · CVPR 2026:cvf:f6b383f93fd270273aaf90413a6caba5CVF · CVPR 2026

来源日期 2026-01-01（仅到年份）

Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward

Gong, Shizhan, Hu, Minda, Zhang, Qiyuan, Ma, Chen, Dou, Qi

原文摘要

Vision-language models (VLMs) have achieved remarkable success across diverse tasks. However, concerns about their trustworthiness persist, particularly regarding tendencies to lean more on textual cues than visual evidence and the risk of producing ungrounded or fabricated responses. To address these issues, we propose Saliency-R1, a framework for improving the interpretability and faithfulness of VLMs reasoning. Specifically, we introduce a novel saliency map technique that efficiently highlights critical image regions contributing to generated tokens without additional computational overhead. This can further be extended to trace how visual information flows through the reasoning process to the final answers, revealing the alignment between the thinking process and the visual context. We use the overlap between the saliency maps and human-annotated bounding boxes as the reward function, and apply Group Relative Policy Optimization (GRPO) to align the salient parts and critical regions, encouraging models to focus on relevant areas when conduct reasoning. Experiments show Saliency-R1 improves reasoning faithfulness, interpretability, and overall task performance.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

CVF · CVPR 2026 ↗PDF ↗