arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

3D 视觉

三维重建、NeRF、Gaussian Splatting、点云和空间智能。

共收录 733 信号源:cs.CV, cs.GR, cs.RO

1. 新视角合成 733 篇

2507.04749 2025-12-30 cs.CV 57%

MatDecompSDF: High-Fidelity 3D Shape and PBR Material Decomposition from Multi-View Images

MatDecompSDF:从多视角图像中恢复高保真3D形状和PBR材质分解

Chengyu Wang, Isabella Bennett, Henry Scott, Liang Zhang, Mei Chen, Hao Li, Rui Zhao

机构 * San Francisco State University 1600 Holloway Avenue San Francisco California USA 94132 Department of Electrical \& Computer Engineering, Boston University 8 Saint Mary’s Street Boston MA USA 02215 University of California, Berkeley 2150 Shattuck Avenue Berkeley California USA 94704 Stanford University 450 Serra Mall Stanford California USA 94305 Carnegie Mellon University 5000 Forbes Avenue Pittsburgh Pennsylvania USA 15213 University of Washington 185 Stevens Way Seattle Washington USA 98195 San Francisco State University Department of Electrical \& Computer Engineering, Boston University University of California, Berkeley Stanford University Carnegie Mellon University University of Washington

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

AI总结 MatDecompSDF通过联合优化SDF、神经场和MLP模型,实现从多视角图像中高保真3D形状和PBR材质的分解。

Comments 12 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20107 2025-12-24 cs.CV 57%

UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis

UMAMI:统一掩码自回归模型和确定性渲染用于视图合成

Thanh-Tung Le, Tuan Pham, Tung Nguyen, Deying Kong, Xiaohui Xie, Stephan Mandt

机构 * UCI(加州大学伯克利分校) UCLA(加州大学洛杉矶分校) Google(谷歌)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

AI总结 UMAMI通过结合掩码自回归模型和确定性渲染,实现了视图合成中图像质量与渲染效率的统一。

Comments Accepted to NeurIPS 2025. The first two authors contributed equally

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.16219 2025-12-19 cs.CV eess.IV 57%

Learning High-Quality Initial Noise for Single-View Synthesis with Diffusion Models

基于扩散模型的学习高质量初始噪声用于单视图合成

Zhihao Zhang, Xuejun Yang, Weihua Liu, Mouquan Shen

机构 * College of Electrical Engineering and Control Science, Nanjing Tech University(电气工程与控制科学学院,南京理工大学) Yongjiang Laboratory(永江实验室)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

AI总结 本文提出了一种基于编码器-解码器网络的框架,通过注入图像语义信息将随机噪声转换为高质量噪声,提升单视图合成性能。

Comments 16 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.05115 2025-12-16 cs.CV 57%

Light-X: Generative 4D Video Rendering with Camera and Illumination Control

Light-X:具有摄像机和照明控制的生成式4D视频渲染

Tianqi Liu, Zhaoxi Chen, Zihao Huang, Shaocong Xu, Saining Zhang, Chongjie Ye, Bohan Li, Zhiguo Cao, Wei Li, Hao Zhao, Ziwei Liu

机构 * S-Lab, NTU(NTU的S-Lab) BAAI HUST(华中科技大学) AIR,THU(清华大学人工智能研究院) FNii, CUHKSZ(CUHKSZ的FNii) SJTU(上海交通大学) EIT (Ningbo)(宁波工程学院)

专题命中 新视角合成 :point cloud(abstract);分类 cs.CV

AI总结 Light-X通过联合控制摄像机轨迹和光照,实现高质量4D视频生成,优于现有方法。

Comments Project Page: https://lightx-ai.github.io/ , Code: https://github.com/TQTQliu/Light-X

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.11645 2025-12-15 cs.CV 57%

FactorPortrait: Controllable Portrait Animation via Disentangled Expression, Pose, and Viewpoint

FactorPortrait: 通过解耦的表情、姿态和视角实现可控的肖像动画

Jiapeng Tang, Kai Li, Chengxiang Yin, Liuhao Ge, Fei Jiang, Jiu Xu, Matthias Nießner, Christian Häne, Timur Bagautdinov, Egor Zakharov, Peihong Guo

机构 * Meta Reality Labs(Meta现实实验室) Technical University of Munich(慕尼黑技术大学)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

AI总结 FactorPortrait通过解耦表情、姿态和视角实现可控肖像动画,利用预训练编码器和3D网格跟踪生成逼真动态效果。

Comments Project page: https://tangjiapeng.github.io/FactorPortrait/

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.10424 2025-12-12 cs.GR 57%

Neural Hamiltonian Deformation Fields for Dynamic Scene Rendering

基于神经哈密顿变形场的动态场景渲染

Hai-Long Qin, Sixian Wang, Guo Lu, Jincheng Dai

专题命中 新视角合成 :Gaussian Splatting(abstract);分类 cs.GR

AI总结 NeHaD通过哈密顿力学建模动态高斯点漂,实现物理真实的动态场景渲染与流媒体能力。

Comments Accepted by ACM SIGGRAPH Asia 2025, project page: https://qin-jingyun.github.io/NeHaD

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.08215 2025-12-10 cs.CV 57%

Blur2Sharp: Human Novel Pose and View Synthesis with Generative Prior Refinement

Blur2Sharp: 基于生成先验细化的人体新颖姿态与视角合成

Chia-Hern Lai, I-Hsuan Lo, Yen-Ku Yeh, Thanh-Nguyen Truong, Ching-Chun Huang

机构 * National Yang Ming Chiao Tung University

专题命中 新视角合成 :NeRF(abstract);分类 cs.CV

AI总结 Blur2Sharp通过整合3D感知神经渲染和扩散模型,实现从单一视角生成清晰且几何一致的新视角图像,提升复杂场景下的姿态与视角合成效果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.04248 2025-12-05 cs.CV cs.AI 57%

MVRoom: Controllable 3D Indoor Scene Generation with Multi-View Diffusion Models

MVRoom: 基于多视角扩散模型的可控3D室内场景生成

Shaoheng Fang, Chaohui Yu, Fan Wang, Qixing Huang

机构 * The University of Texas at Austin(德克萨斯大学奥斯汀分校) DAMO Academy, Alibaba Group(阿里巴巴达摩院) Hupan Lab(虎斑实验室)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

AI总结 MVRoom通过多视角扩散模型实现可控的3D室内场景生成,结合布局感知的极线注意力机制和迭代框架,提升多视角一致性和生成质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.03045 2025-12-03 cs.CV 57%

CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models

CAMEO:多视图扩散模型中的对应-注意力对齐

Minkyung Kwon, Jinhyeok Choi, Jiho Park, Seonghu Jeon, Jinhyuk Jang, Junyoung Seo, Minseop Kwak, Jin-Hwa Kim, Seungryong Kim

机构 * KAIST AI(韩国科学技术院人工智能研究中心) NAVER AI Lab(NAVER人工智能实验室) SNU AIIS(延世大学人工智能研究所)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

AI总结 CAMEO通过几何对应监督注意力图,提升多视图扩散模型的训练效率和生成质量。

Comments Project page: https://cvlab-kaist.github.io/CAMEO/

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.01178 2025-12-02 cs.CV 57%

VSRD++: Autolabeling for 3D Object Detection via Instance-Aware Volumetric Silhouette Rendering

VSRD++: 通过实例感知的体素轮廓渲染实现3D目标检测的自标注

Zihua Liu, Hiroki Sakuma, Masatoshi Okutomi

机构 * Department of System and Control Engineering, Institute of Science Tokyo, Tokyo(系统与控制工程系,科学东京研究所)

专题命中 新视角合成 :point cloud(abstract);分类 cs.CV

AI总结 VSRD++通过实例感知的体素轮廓渲染技术实现单目3D目标检测的弱监督自标注,有效提升静态和动态场景下的检测性能。

Comments arXiv admin note: text overlap with arXiv:2404.00149

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.03861 2025-11-26 cs.CV 57%

Refinement of Monocular Depth Maps via Multi-View Differentiable Rendering

通过多视角可微渲染细化单目深度图

Laura Fink, Linus Franke, Bernhard Egger, Joachim Keinert, Marc Stamminger

机构 * Friedrich-Alexander-Universität Erlangen-Nürnberg(埃朗根-纽伦堡弗里德里希-亚历山大大学) Fraunhofer IIS Erlangen(弗劳恩霍夫研究所埃朗根)

专题命中 新视角合成 :point cloud(abstract);分类 cs.CV

AI总结 本文提出通过多视角可微渲染优化,提升单目深度图的精度与一致性,实现更高质量的深度估计。

Comments 8 pages main paper + 3 pages of references + 6 pages appendix

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10496 2025-11-14 cs.CV cs.AI 57%

Cameras as Relative Positional Encoding

Ruilong Li, Brent Yi, Junchen Liu, Hang Gao, Yi Ma, Angjoo Kanazawa

机构 * UC Berkeley(伯克利大学) NVIDIA(NVIDIA公司) HKU(香港大学)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

Comments Project Page: https://www.liruilong.cn/prope/

Journal ref NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.08178 2025-11-12 cs.CV 57%

WarpGAN: Warping-Guided 3D GAN Inversion with Style-Based Novel View Inpainting

Kaitao Huang, Yan Yan, Jing-Hao Xue, Hanzi Wang

机构 * Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, P.R. China(中国教育部多媒体可信感知与高效计算重点实验室,厦门大学) Department of Statistical Science, University College London, UK(伦敦大学学院统计学系)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.06846 2025-11-11 cs.CV 57%

Gaussian-Augmented Physics Simulation and System Identification with Complex Colliders

Federico Vasile, Ri-Zhao Qiu, Lorenzo Natale, Xiaolong Wang

机构 * Istituto Italiano di Tecnologia(意大利技术研究院) UC San Diego(加州大学圣地亚哥分校)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

Comments Accepted to NeurIPS 2025. Project website: https://as-diffmpm.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.13030 2025-11-04 cs.CV 57%

WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild

Morris Alper, David Novotny, Filippos Kokkinos, Hadar Averbuch-Elor, Tom Monnier

机构 * Tel Aviv University(特拉维夫大学) Meta AI Cornell University(康奈尔大学)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

Comments Accepted to NeurIPS 2025. Project page: https://wildcat3d.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21657 2025-11-03 cs.CV 57%

FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction

Yixiang Dai, Fan Jiang, Chiyu Wang, Mu Xu, Yonggang Qi

机构 * AMAP, Alibaba Group(阿里集团AMAP) Beijing University of Posts and Telecommunications(北京邮电大学)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16873 2025-11-03 cs.CV 57%

$\mathtt{M^3VIR}$: A Large-Scale Multi-Modality Multi-View Synthesized Benchmark Dataset for Image Restoration and Content Creation

Yuanzhi Li, Lebin Zhou, Nam Ling, Zhenghao Chen, Wei Wang, Wei Jiang

机构 * Santa Clara University(圣克拉拉大学) University of Newcastle(新castle大学) Futurewei Technologies, Inc.(未来科技公司)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20385 2025-10-24 cs.CV 57%

Positional Encoding Field

Yunpeng Bai, Haoxiang Li, Qixing Huang

机构 * University of Texas at Austin(德克萨斯大学奥斯汀分校) Pixocial Technology(Pixocial技术)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

Comments 8 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20132 2025-10-24 cs.CV 57%

Inverse Image-Based Rendering for Light Field Generation from Single Images

Hyunjun Jung, Hae-Gon Jeon

机构 * GIST AI Graduated School(GIST人工智能研究生院) Yonsei University(延世大学)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08279 2025-10-13 cs.CV cs.AI 57%

Learning Neural Exposure Fields for View Synthesis

Michael Niemeyer, Fabian Manhardt, Marie-Julie Rakotosaona, Michael Oechsle, Christina Tsalicoglou, Keisuke Tateno, Jonathan T. Barron, Federico Tombari

机构 * Google(谷歌)

专题命中 新视角合成 :3D reconstruction(abstract);分类 cs.CV

Comments Accepted to NeurIPS 2025. Project page available at https://m-niemeyer.github.io/nexf/index.html

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.18213 2025-10-03 cs.SD cs.CV eess.AS 57%

NeRAF: 3D Scene Infused Neural Radiance and Acoustic Fields

Amandine Brunetto, Sascha Hornauer, Fabien Moutarde

机构 * Center for Robotics, Mines Paris - PSL University Paris, France(机器人中心,巴黎 Mines Paris - PSL 大学)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

Comments ICLR 2025 (Poster). Camera ready version. Project Page: https://amandinebtto.github.io/NeRAF; 24 pages, 13 figures

Journal ref The Thirteenth International Conference on Learning Representations, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.15717 2025-09-22 cs.RO 57%

Imagination at Inference: Synthesizing In-Hand Views for Robust Visuomotor Policy Inference

Haoran Ding, Anqing Duan, Zezhou Sun, Dezhen Song, Yoshihiko Nakamura

机构 * Department of Robotics, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)(机器人系,Mohamed bin Zayed人工智能大学)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.RO

Comments Submitted to IEEE for possible publication, under review

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.11114 2025-09-16 cs.CV cs.LG 57%

WildSmoke: Ready-to-Use Dynamic 3D Smoke Assets from a Single Video in the Wild

Yuqiu Liu, Jialin Song, Manolis Savva, Wuyang Chen

机构 * Simon Fraser University(西蒙弗雷泽大学)

专题命中 新视角合成 :3D vision(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.10868 2025-09-05 cs.CV 57%

TexVerse: A Universe of 3D Objects with High-Resolution Textures

Yibo Zhang, Li Zhang, Rui Ma, Nan Cao

机构 * Shanghai Innovation Institute(上海创新研究院) Jilin University(吉林大学) Fudan University(复旦大学) Tongji University(同济大学)

专题命中 新视角合成 :3D vision(abstract);分类 cs.CV

Comments https://github.com/yiboz2001/TexVerse

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.00843 2025-09-03 cs.CV cs.AI 57%

Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion

Xueyang Kang, Zhengkang Xiang, Zezheng Zhang, Kourosh Khoshelham

机构 * University of Melbourne(墨尔本大学)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

Comments 26 pages, 30 figures, 2025 ACM Multimedia

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.12929 2025-08-12 cs.CV 57%

AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction

Xuying Zhang, Yupeng Zhou, Kai Wang, Yikai Wang, Zhen Li, Shaohui Jiao, Daquan Zhou, Qibin Hou, Ming-Ming Cheng

机构 * VCIP, CS, Nankai University(南开大学计算机科学与技术学院) NKIARI, Shenzhen Futian(深圳南山人工智能研究院) Tsinghua University(清华大学) ByteDance Inc.(字节跳动公司)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

Comments Accepted at ICCV 2025; Project page: https://github.com/HVision-NKU/AR123

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.04467 2025-08-07 cs.CV 57%

4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation

Shuzhou Yang, Xiaodong Cun, Xiaoyu Li, Yaowei Li, Jian Zhang

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2206.09736 2025-08-05 cs.CV eess.IV 57%

Geo-NI: Geometry-aware Neural Interpolation for Light Field Rendering

Gaochang Wu, Yuemei Zhou, Yebin Liu, Lu Fang, Tianyou Chai

机构 * State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University(合成自动化过程工业国家重点实验室,东北大学) Department of Automation, Tsinghua University(自动化系,清华大学) Department of Electronic Engineering, Tsinghua University(电子工程系,清华大学) Beijing National Research Center for Information Science and Technology(北京信息科学与技术国家研究中心)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

Comments Accepted by IEEE TPAMI, 16 pages, 14 figures, 6 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.05166 2025-07-22 cs.CV 57%

CD-NGP: A Fast Scalable Continual Representation for Dynamic Scenes

Zhenhuan Liu, Shuai Liu, Zhiwei Ning, Jie Yang, Yifan Zuo, Yuming Fang, Wei Liu

机构 * Dept. of Automation, Shanghai Jiao Tong University(自动化系,上海交通大学)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

Comments 18 pages in total

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.02299 2025-07-04 cs.CV 57%

DreamComposer++: Empowering Diffusion Models with Multi-View Conditions for 3D Content Generation

Yunhan Yang, Shuo Chen, Yukun Huang, Xiaoyang Wu, Yuan-Chen Guo, Edmund Y. Lam, Hengshuang Zhao, Tong He, Xihui Liu

机构 * The University of Hong Kong(香港大学) Tsinghua University(清华大学) Vast Shanghai AI Laboratory(上海人工智能实验室)

专题命中 新视角合成 :novel view synthesis(abstract);分类 cs.CV

Comments Accepted by TPAMI, extension of CVPR 2024 paper DreamComposer

详情

展开后加载摘要…

URL PDF HTML 收藏