3D 视觉 - arXivDaily 专题

2105.13016 2022-01-19 cs.CV 70%

Stylizing 3D Scene via Implicit Representation and HyperNetwork

Pei-Ze Chiang, Meng-Shiun Tsai, Hung-Yu Tseng, Wei-sheng Lai, Wei-Chen Chiu

专题命中 NeRF ：NeRF(abstract)；novel view synthesis(abstract)；分类 cs.CV

Comments Accepted to WACV2022; Project page: https://ztex08010518.github.io/3dstyletransfer/

2111.13112 2021-11-29 cs.CV 70%

VaxNeRF: Revisiting the Classic for Voxel-Accelerated Neural Radiance Field

Naruya Kondo, Yuya Ikeda, Andrea Tagliasacchi, Yutaka Matsuo, Yoichi Ochiai, Shixiang Shane Gu

专题命中 NeRF ：NeRF(abstract)；3D reconstruction(abstract)；分类 cs.CV

2104.10078 2021-10-11 cs.CV 70%

UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

Michael Oechsle, Songyou Peng, Andreas Geiger

专题命中 NeRF ：NeRF(abstract)；novel view synthesis(abstract)；分类 cs.CV

Comments ICCV 2021 oral

2103.15606 2021-08-19 cs.CV 70%

GNeRF: GAN-based Neural Radiance Field without Posed Camera

Quan Meng, Anpei Chen, Haimin Luo, Minye Wu, Hao Su, Lan Xu, Xuming He, Jingyi Yu

专题命中 NeRF ：NeRF(abstract)；novel view synthesis(abstract)；分类 cs.CV

Comments ICCV 2021 (Oral)

2104.09877 2021-04-21 cs.CV 70%

Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry

Dawa Derksen, Dario Izzo

专题命中 NeRF ：NeRF(abstract)；novel view synthesis(abstract)；分类 cs.CV

Comments Accepted to CVPR2021 - EarthVision

2104.06405 2021-08-20 cs.CV cs.GR cs.LG cs.RO 69%

BARF: Bundle-Adjusting Neural Radiance Fields

Chen-Hsuan Lin, Wei-Chiu Ma, Antonio Torralba, Simon Lucey

专题命中 NeRF ：NeRF(abstract,comments)；分类 cs.CV、cs.GR、cs.RO

Comments Accepted to ICCV 2021 as oral presentation (project page & code: https://chenhsuanlin.bitbucket.io/bundle-adjusting-NeRF)

2601.03869 2026-03-09 cs.CV cs.GR cs.LG cs.RO 67%

Bayesian Monocular Depth Refinement via Neural Radiance Fields

基于神经辐射场的贝叶斯单目深度细化

Arun Muthukkumar

机构 * Department of Computer Science Illinois Mathematics ； Science Academy Aurora, United States

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.GR、cs.RO

AI总结本文提出MDENeRF，通过神经辐射场和贝叶斯融合改进单目深度估计，提升场景理解的精细几何细节。

Comments IEEE 8th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI 2025)

Journal ref Proc. IEEE 8th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI), pp. 488-492, 2025

2510.07667 2025-10-10 eess.IV 67%

An Energy-Efficient Edge Coprocessor for Neural Rendering with Explicit Data Reuse Strategies

Binzhe Yuan, Xiangyu Zhang, Zeyu Zheng, Yuefeng Zhang, Haochuan Wan, Zhechen Yuan, Junsheng Chen, Yunxiang He, Junran Ding, Xiaoming Zhang, Chaolin Rao, Wenyan Su, Pingqiang Zhou, Jingyi Yu, Xin Lou

专题命中 NeRF ：NeRF(abstract)；3D reconstruction(abstract)

Comments 11 pages, 17 figures, 2 tables

2405.12155 2024-06-19 cs.IT math.IT 67%

Embracing Radiance Field Rendering in 6G: Over-the-Air Training and Inference with 3D Contents

Guanlin Wu, Zhonghao Lyu, Juyong Zhang, Jie Xu

专题命中 NeRF ：NeRF(abstract)；Gaussian Splatting(abstract)

Comments 16 pages,7 figures

2406.10474 2024-06-18 cs.DC 67%

Federated Neural Radiance Field for Distributed Intelligence

Yintian Zhang, Ziyu Shao

专题命中 NeRF ：NeRF(abstract)；novel view synthesis(abstract)

2406.04155 2024-06-07 cs.CV cs.AI cs.GR cs.LG cs.RO 67%

Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization

Takuhiro Kaneko

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.GR、cs.RO

Comments Accepted to CVPR 2024. Project page: https://www.kecl.ntt.co.jp/people/kaneko.takuhiro/projects/lpo/

2308.02751 2023-08-22 cs.CV cs.AI cs.GR cs.LG cs.RO 67%

NeRFs: The Search for the Best 3D Representation

Ravi Ramamoorthi

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.GR、cs.RO

Comments Updated based on feedback in-person and via e-mail at SIGGRAPH 2023. In particular, I have added references and discussion of seminal SIGGRAPH image-based rendering papers, and better put the recent Kerbl et al. work in context, with more references

2201.12204 2022-11-11 cs.LG 67%

From data to functa: Your data point is a function and you can treat it like one

Emilien Dupont, Hyunjik Kim, S. M. Ali Eslami, Danilo Rezende, Dan Rosenbaum

专题命中 NeRF ：NeRF(abstract)；novel view synthesis(abstract)

2308.10902 2023-09-01 cs.CV cs.GR 66%

CamP: Camera Preconditioning for Neural Radiance Fields

Keunhong Park, Philipp Henzler, Ben Mildenhall, Jonathan T. Barron, Ricardo Martin-Brualla

专题命中 NeRF ：NeRF(abstract,comments)；分类 cs.CV、cs.GR

Comments SIGGRAPH Asia 2023, Project page: https://camp-nerf.github.io

2208.00277 2023-05-31 cs.CV cs.GR cs.LG 66%

MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures

Zhiqin Chen, Thomas Funkhouser, Peter Hedman, Andrea Tagliasacchi

专题命中 NeRF ：NeRF(abstract,comments)；分类 cs.CV、cs.GR

Comments CVPR 2023. Project page: https://mobile-nerf.github.io, code: https://github.com/google-research/jax3d/tree/main/jax3d/projects/mobilenerf

2201.07786 2022-02-11 cs.CV cs.GR cs.LG cs.MM cs.SD eess.AS 66%

Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation

Xian Liu, Yinghao Xu, Qianyi Wu, Hang Zhou, Wayne Wu, Bolei Zhou

专题命中 NeRF ：NeRF(abstract,comments)；分类 cs.CV、cs.GR

Comments 12 pages, 3 figures. Project page: https://alvinliu0.github.io/projects/SSP-NeRF

2103.14645 2021-03-29 cs.CV cs.GR 66%

Baking Neural Radiance Fields for Real-Time View Synthesis

Peter Hedman, Pratul P. Srinivasan, Ben Mildenhall, Jonathan T. Barron, Paul Debevec

专题命中 NeRF ：NeRF(abstract,comments)；分类 cs.CV、cs.GR

Comments Project page: https://nerf.live

2603.27151 2026-03-31 cs.GR cs.CV 62%

DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification

DiffSoup：三角汤的直接可微化着色以实现极端辐射场简化

Kenji Tojo, Bernd Bickel, Nobuyuki Umetani

机构 * The University of Tokyo（东京大学）； ETH Zürich（苏黎世联邦理工学院）

专题命中 NeRF ：Gaussian Splatting(abstract)；分类 cs.CV、cs.GR

AI总结本文提出DiffSoup，一种利用少量三角形和神经纹理的辐射场表示，通过随机遮罩实现直接可微的二进制不透明度，从而在无需平滑着色的情况下实现高效的实时渲染。

2601.07242 2026-03-24 cs.RO cs.CV 62%

HERE: Hierarchical Active Exploration of Radiance Field with Epistemic Uncertainty Minimization

HERE：基于证据深度学习的辐射场分层主动探索

Taekbeom Lee, Dabin Kim, Youngseok Jang, H. Jin Kim

机构 * Department of Aerospace Engineering, Seoul National University（航空航天工程系，首尔国立大学）

专题命中 NeRF ：3D reconstruction(abstract)；分类 cs.CV、cs.RO

AI总结本文提出HERE框架，通过主动学习策略生成相机轨迹，结合证据深度学习量化epistemic不确定性，提升3D场景重建的精度和效率。

Comments Accepted to IEEE RA-L. The first two authors contributed equally

2603.17236 2026-03-19 cs.RO cs.CV 62%

Neural Radiance Maps for Extraterrestrial Navigation and Path Planning

神经辐射图用于外星导航和路径规划

Adam Dai, Shubh Gupta, Grace Gao

机构 * Stanford University（斯坦福大学）

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.RO

AI总结本文提出利用神经辐射场构建地图，用于自主导航中的路径规划，通过整合局部和全局信息，实现更高效的路径规划。

Comments Published in the Proceedings of the ION GNSS+ 2023 Conference

2512.21692 2026-03-13 cs.CV cs.GR 62%

ShinyNeRF: Digitizing Anisotropic Appearance in Neural Radiance Fields

ShinyNeRF：神经辐射场中各向异性外观的数字化

Albert Barreiro, Roger Marí, Rafael Redondo, Gloria Haro, Carles Bosch

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.GR

AI总结 ShinyNeRF 通过联合估计表面法线、切线、镜面浓度和各向异性程度，实现了对各向异性镜面反射的高效数字化，同时提供了物理可解释的材料属性编辑。

2510.08491 2026-03-03 cs.GR cs.CV 62%

Splat the Net: Radiance Fields with Splattable Neural Primitives

Splat the Net: 基于可拆分神经原语的光场

Xilong Zhou, Bao-Huy Nguyen, Loïc Magne, Vladislav Golyanik, Thomas Leimkühler, Christian Theobalt

机构 * Max Planck Institute for Informatics（马克斯·普朗克研究所信息学研究所）

专题命中 NeRF ：Gaussian Splatting(abstract)；分类 cs.CV、cs.GR

AI总结 Splat the Net提出了一种新的体积表示方法，结合神经网络的表达力和原语散射的效率，通过可拆分的神经原语实现高效且高质量的3D场景建模。

2312.12122 2026-02-11 cs.CV cs.GR 62%

ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fields

ZS-SRT: 一种高效的零样本超分辨率训练方法用于神经辐射场

Xiang Feng, Yongbo He, Yubo Wang, Chengkai Wang, Zhenzhong Kuang, Jiajun Ding, Feiwei Qin, Jun Yu, Jianping Fan

机构 * School of Computer Science and Technology, Hangzhou Dianzi University（杭州电子科技大学计算机科学与技术学院）； AI Lab at Lenovo Research（联想研究院人工智能实验室）

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.GR

AI总结 ZS-SRT提出了一种无需高分辨率数据的NeRF超分辨率训练方法，通过内部学习和反向渲染提升训练效率与图像质量。

Journal ref Neurocomputing, Volume 590, 14 July 2024, Article 127714

2507.02900 2026-01-22 cs.CV cs.AI cs.GR cs.HC cs.MM 62%

Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions

推进说话头生成：多模态方法、数据集、评估指标和损失函数的全面综述

Vineet Kumar Rakesh, Soumya Mazumdar, Research Pratim Maity, Sarbajit Pal, Amitabha Das, Tapas Samanta

机构 * Engineering Sciences, Homi Bhabha National Institute Training School Complex（工程科学，霍米·巴赫瓦全国研究所培训学校）； Computer and Informatics Group, VECC 1/AF（计算机与信息组，VECC 1/AF）

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.GR

AI总结本文全面综述了说话头生成的多模态方法、数据集、评估指标和损失函数，探讨了技术挑战与未来发展方向。

2601.00207 2026-01-05 cs.CV cs.RO 62%

CropNeRF: A Neural Radiance Field-Based Framework for Crop Counting

CropNeRF: 一种基于神经辐射场的作物计数框架

Md Ahmed Al Muzaddid, William J. Beksi

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.RO

AI总结 CropNeRF通过3D实例分割实现精确作物计数，结合神经辐射场与可见性评分，无需参数调优，验证于多个农业数据集，表现优于现有方法。

Comments 8 pages, 10 figures, and 2 tables

2510.03163 2025-12-05 cs.CV cs.GR 62%

ROGR: Relightable 3D Objects using Generative Relighting

ROGR：基于生成光照的可重照明3D物体

Jiapeng Tang, Matthew Levine, Dor Verbin, Stephan J. Garbin, Matthias Nießner, Ricardo Martin Brualla, Pratul P. Srinivasan, Philipp Henzler

机构 * Google Research（谷歌研究）； Google Deepmind（谷歌DeepMind）； Technical University of Munich（慕尼黑技术大学）

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.GR

AI总结 ROGR通过生成光照模型实现可重照明的3D物体重建，采用双分支架构的光照条件NeRF，高效生成任意环境光照下的物体外观。

Comments NeurIPS 2025 Spotlight. Project page: https://tangjiapeng.github.io/ROGR

2405.10255 2025-10-22 cs.CV cs.RO 62%

When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models

Xianzheng Ma, Brandon Smart, Yash Bhalgat, Shuai Chen, Xinghui Li, Jian Ding, Jindong Gu, Dave Zhenyu Chen, Songyou Peng, Jia-Wang Bian, Philip H Torr, Marc Pollefeys, Matthias Nießner, Ian D Reid, Angel X. Chang, Iro Laina, Victor Adrian Prisacariu

机构 * University of Oxford（牛津大学）； King Abdullah University of Science and Technology（国王 Abdullah 科学与技术大学）； Technical University of Munich（慕尼黑技术大学）； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）； Simon Fraser University（西蒙·弗雷泽大学）； ETH Zurich（苏黎世联邦理工学院）

专题命中 NeRF ：point cloud(abstract)；分类 cs.CV、cs.RO

Comments 2nd version update to Jun.2025

2502.02657 2025-10-10 cs.RO cs.CV 62%

SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification

Yifu Tao, Maurice Fallon

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.RO

Comments Accepted by T-RO. Webpage: https://dynamic.robots.ox.ac.uk/projects/silvr/

2407.01781 2025-09-30 cs.CV cs.GR cs.LG 62%

fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence

Francis Williams, Jiahui Huang, Jonathan Swartz, Gergely Klár, Vijay Thakkar, Matthew Cong, Xuanchi Ren, Ruilong Li, Clement Fuji-Tsang, Sanja Fidler, Eftychios Sifakis, Ken Museth

机构 * NVIDIA Research（NVIDIA研究）； University of Wisconsin-Madison（威斯康星大学麦迪逊分校）

专题命中 NeRF ：point cloud(abstract)；分类 cs.CV、cs.GR

2404.05236 2025-07-15 cs.CV cs.GR 62%

Stylizing Sparse-View 3D Scenes with Hierarchical Neural Representation

Y. Wang, A. Gao, Y. Gong, Y. Zeng

机构 * Southern University of Science and Technology（南方科技大学）

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV、cs.GR

Journal ref 2025

1. NeRF 1354 篇

Stylizing 3D Scene via Implicit Representation and HyperNetwork

VaxNeRF: Revisiting the Classic for Voxel-Accelerated Neural Radiance Field

UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

GNeRF: GAN-based Neural Radiance Field without Posed Camera

Shadow Neural Radiance Fields for Multi-view Satellite Photogrammetry

BARF: Bundle-Adjusting Neural Radiance Fields

Bayesian Monocular Depth Refinement via Neural Radiance Fields

An Energy-Efficient Edge Coprocessor for Neural Rendering with Explicit Data Reuse Strategies

Embracing Radiance Field Rendering in 6G: Over-the-Air Training and Inference with 3D Contents

Federated Neural Radiance Field for Distributed Intelligence

Improving Physics-Augmented Continuum Neural Radiance Field-Based Geometry-Agnostic System Identification with Lagrangian Particle Optimization

NeRFs: The Search for the Best 3D Representation

From data to functa: Your data point is a function and you can treat it like one

CamP: Camera Preconditioning for Neural Radiance Fields

MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures

Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation

Baking Neural Radiance Fields for Real-Time View Synthesis

DiffSoup: Direct Differentiable Rasterization of Triangle Soup for Extreme Radiance Field Simplification

HERE: Hierarchical Active Exploration of Radiance Field with Epistemic Uncertainty Minimization

Neural Radiance Maps for Extraterrestrial Navigation and Path Planning

ShinyNeRF: Digitizing Anisotropic Appearance in Neural Radiance Fields

Splat the Net: Radiance Fields with Splattable Neural Primitives

ZS-SRT: An Efficient Zero-Shot Super-Resolution Training Method for Neural Radiance Fields

Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions

CropNeRF: A Neural Radiance Field-Based Framework for Crop Counting

ROGR: Relightable 3D Objects using Generative Relighting

When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models

SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification

fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence

Stylizing Sparse-View 3D Scenes with Hierarchical Neural Representation