3D 视觉 - arXivDaily 专题

2206.04669 2022-06-10 cs.CV 57%

Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields

Mingtong Zhang, Shuhong Zheng, Zhipeng Bao, Martial Hebert, Yu-Xiong Wang

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

2206.00878 2022-06-03 cs.CV 57%

EfficientNeRF: Efficient Neural Radiance Fields

Tao Hu, Shu Liu, Yilun Chen, Tiancheng Shen, Jiaya Jia

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

2111.10427 2022-05-19 cs.CV 57%

DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering

Liwen Wu, Jae Yong Lee, Anand Bhattad, Yuxiong Wang, David Forsyth

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

2205.05922 2022-05-13 cs.CV 57%

Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation

Jian Zhang, Yuanqing Zhang, Huan Fu, Xiaowei Zhou, Bowen Cai, Jinchi Huang, Rongfei Jia, Binqiang Zhao, Xing Tang

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

2112.01523 2022-05-11 cs.CV 57%

Learning Neural Light Fields with Ray-Space Embedding Networks

Benjamin Attal, Jia-Bin Huang, Michael Zollhoefer, Johannes Kopf, Changil Kim

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments CVPR 2022 camera ready revision. Major changes include: 1. Additional comparison to NeX on Stanford, RealFF, Shiny datasets 2. Experiment on 360 degree lego bulldozer scene in the appendix, using Pluecker parameterization 3. Moving student-teacher results to the appendix 4. Clarity edits -- in particular, making it clear that our Stanford evaluation *does not* use subdivision

2111.09996 2022-04-27 cs.CV 57%

LOLNeRF: Learn from One Look

Daniel Rebain, Mark Matthews, Kwang Moo Yi, Dmitry Lagun, Andrea Tagliasacchi

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

Comments See https://lolnerf.github.io for additional results

2112.10759 2022-04-19 cs.CV 57%

3D-aware Image Synthesis via Learning Structural and Textural Representations

Yinghao Xu, Sida Peng, Ceyuan Yang, Yujun Shen, Bolei Zhou

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments CVPR 2022 camera-ready, Project page: https://genforce.github.io/volumegan/

2204.05735 2022-04-13 cs.CV 57%

GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation

Shin-Fang Chng, Sameera Ramasinghe, Jamie Sherrah, Simon Lucey

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments Project page: https://sfchng.github.io/garf/

2202.01020 2022-04-11 eess.IV cs.CV 57%

MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray

Abril Corona-Figueroa, Jonathan Frawley, Sam Bond-Taylor, Sarath Bethapudi, Hubert P. H. Shum, Chris G. Willcocks

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

Comments 6 pages, 4 figures, accepted at IEEE EMBC 2022

2204.03593 2022-04-08 cs.CV 57%

AutoRF: Learning 3D Object Radiance Fields from Single View Observations

Norman Müller, Andrea Simonelli, Lorenzo Porzi, Samuel Rota Bulò, Matthias Nießner, Peter Kontschieder

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

Comments CVPR 2022. Project page: https://sirwyver.github.io/AutoRF/

2203.15798 2022-03-30 cs.CV 57%

DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars

Amit Raj, Umar Iqbal, Koki Nagano, Sameh Khamis, Pavlo Molchanov, James Hays, Jan Kautz

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments Project page at https://dracon-avatars.github.io/

2107.07905 2022-03-17 cs.CV cs.AI 57%

Unsupervised Discovery of Object Radiance Fields

Hong-Xing Yu, Leonidas J. Guibas, Jiajun Wu

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

Comments ICLR 2022. Project page: https://kovenyu.com/uorf/

2203.06457 2022-03-15 cs.CV 57%

3D-GIF: 3D-Controllable Object Generation via Implicit Factorized Representations

Minsoo Lee, Chaeyeon Chung, Hojun Cho, Minjung Kim, Sanghun Jung, Jaegul Choo, Minhyuk Sung

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

2110.00168 2022-01-05 cs.RO 57%

Vision-Only Robot Navigation in a Neural Radiance World

Michal Adamkiewicz, Timothy Chen, Adam Caccavale, Rachel Gardner, Preston Culbertson, Jeannette Bohg, Mac Schwager

专题命中 NeRF ：NeRF(abstract)；分类 cs.RO

2112.09061 2021-12-17 cs.CV cs.AI cs.LG 57%

Solving Inverse Problems with NerfGANs

Giannis Daras, Wen-Sheng Chu, Abhishek Kumar, Dmitry Lagun, Alexandros G. Dimakis

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments 16 pages, 18 figures

2112.05598 2021-12-13 cs.CV 57%

PERF: Performant, Explicit Radiance Fields

Sverker Rasmuson, Erik Sintorn, Ulf Assarsson

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

2109.15271 2021-12-07 cs.CV 57%

TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis

Benjamin Attal, Eliot Laidlaw, Aaron Gokaslan, Changil Kim, Christian Richardt, James Tompkin, Matthew O'Toole

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2021. Web page: https://imaging.cs.cmu.edu/torf/ NeurIPS camera ready updates -- added quantitative comparisons to new methods, visual side-by-side comparisons performed on larger baseline camera sequences

2110.05594 2021-10-13 cs.CV 57%

Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo

Berk Kaya, Suryansh Kumar, Francesco Sarno, Vittorio Ferrari, Luc Van Gool

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

Comments Accepted for publication at IEEE/CVF WACV 2022. 18 pages

2109.01129 2021-10-06 cs.CV 57%

NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo

Yi Wei, Shaohui Liu, Yongming Rao, Wang Zhao, Jiwen Lu, Jie Zhou

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments To appear in ICCV 2021 (Oral). Project page: https://weiyithu.github.io/NerfingMVS/

2109.02123 2021-09-29 cs.CV 57%

Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representations

Jianxiong Shen, Adria Ruiz, Antonio Agudo, Francesc Moreno-Noguer

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

2106.13629 2021-09-08 cs.CV 57%

Animatable Neural Radiance Fields from Monocular RGB Videos

Jianchuan Chen, Ying Zhang, Di Kang, Xuefei Zhe, Linchao Bao, Xu Jia, Huchuan Lu

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments 12 pages, 12 figures

2108.13826 2021-09-03 cs.CV 57%

Self-Calibrating Neural Radiance Fields

Yoonwoo Jeong, Seokjun Ahn, Christopher Choy, Animashree Anandkumar, Minsu Cho, Jaesik Park

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments Accepted in ICCV21, Project Page: https://postech-cvlab.github.io/SCNeRF/

2103.13744 2021-08-03 cs.CV 57%

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

Christian Reiser, Songyou Peng, Yiyi Liao, Andreas Geiger

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments ICCV 2021. Code, pretrained models and an interactive viewer are available at https://github.com/creiser/kilonerf/

2106.10859 2021-06-22 cs.CV 57%

Moving in a 360 World: Synthesizing Panoramic Parallaxes from a Single Panorama

Ching-Yu Hsu, Cheng Sun, Hwann-Tzong Chen

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

2105.06405 2021-05-14 cs.CV 57%

Vision-based Neural Scene Representations for Spacecraft

Anne Mergy, Gurvan Lecuyer, Dawa Derksen, Dario Izzo

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

2103.10380 2021-04-16 cs.CV 57%

FastNeRF: High-Fidelity Neural Rendering at 200FPS

Stephan J. Garbin, Marek Kowalski, Matthew Johnson, Jamie Shotton, Julien Valentin

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments main paper: 10 pages, 6 figures; supplementary: 10 pages, 17 figures

2104.06935 2021-04-15 cs.CV cs.LG 57%

Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes

Julian Chibane, Aayush Bansal, Verica Lazova, Gerard Pons-Moll

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021

Journal ref IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2021

2104.01148 2021-04-05 cs.CV cs.LG stat.ML 57%

Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation

Karl Stelzner, Kristian Kersting, Adam R. Kosiorek

专题命中 NeRF ：NeRF(abstract)；分类 cs.CV

Comments 15 pages, 3 figures. For project page with videos, see http://stelzner.github.io/obsurf/

2007.02442 2021-03-31 cs.CV 57%

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

Katja Schwarz, Yiyi Liao, Michael Niemeyer, Andreas Geiger

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

Journal ref Advances in Neural Information Processing Systems, NeurIPS 2020

2604.23310 2026-04-28 cs.NI 50%

RadTwin: Generalizable Wireless Digital Twin for Dynamic Environments

RadTwin: 适用于动态环境的通用无线数字孪生

Yuru Zhang, Ming Zhao, Qiang Liu, Ahmed Alkhateeb, Abhishek K. Agrawal, Qi Qu

专题命中 NeRF ：point cloud(abstract)

AI总结本文提出RadTwin框架，通过场景几何条件化建模，实现动态环境下的无线数字孪生，实验显示其在SSIM和LPIPS指标上优于NeRF2，具备高泛化性和数据效率。

Comments This paper is accepted by IEEE ICCCN 2026

1. NeRF 1355 篇

Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields

EfficientNeRF: Efficient Neural Radiance Fields

DIVeR: Real-time and Accurate Neural Radiance Fields with Deterministic Integration for Volume Rendering

Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation

Learning Neural Light Fields with Ray-Space Embedding Networks

LOLNeRF: Learn from One Look

3D-aware Image Synthesis via Learning Structural and Textural Representations

GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimation

MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray

AutoRF: Learning 3D Object Radiance Fields from Single View Observations

DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance Fields for Articulated Avatars

Unsupervised Discovery of Object Radiance Fields

3D-GIF: 3D-Controllable Object Generation via Implicit Factorized Representations

Vision-Only Robot Navigation in a Neural Radiance World

Solving Inverse Problems with NerfGANs

PERF: Performant, Explicit Radiance Fields

TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis

Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo

NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo

Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representations

Animatable Neural Radiance Fields from Monocular RGB Videos

Self-Calibrating Neural Radiance Fields

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

Moving in a 360 World: Synthesizing Panoramic Parallaxes from a Single Panorama

Vision-based Neural Scene Representations for Spacecraft

FastNeRF: High-Fidelity Neural Rendering at 200FPS

Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes

Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

RadTwin: Generalizable Wireless Digital Twin for Dynamic Environments