3D 视觉 - arXivDaily 专题

2310.16831 2023-10-31 cs.CV cs.GR cs.LG 73%

PERF: Panoramic Neural Radiance Field from a Single Panorama

Guangcong Wang, Peng Wang, Zhaoxi Chen, Wenping Wang, Chen Change Loy, Ziwei Liu

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

Comments Project Page: https://perf-project.github.io/ , Code: https://github.com/perf-project/PeRF

2310.13670 2023-10-23 cs.CV cs.AI cs.GR cs.LG 73%

ManifoldNeRF: View-dependent Image Feature Supervision for Few-shot Neural Radiance Fields

Daiju Kanaoka, Motoharu Sonogashira, Hakaru Tamukoh, Yasutomo Kawanishi

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

Comments Accepted by BMVC2023

2309.10684 2023-09-20 cs.CV cs.GR 73%

Locally Stylized Neural Radiance Fields

Hong-Wing Pang, Binh-Son Hua, Sai-Kit Yeung

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

Comments ICCV 2023

2308.03772 2023-08-09 cs.CV cs.AI cs.GR cs.LG eess.IV 73%

Improved Neural Radiance Fields Using Pseudo-depth and Fusion

Jingliang Li, Qiang Zhou, Chaohui Yu, Zhengda Lu, Jun Xiao, Zhibin Wang, Fan Wang

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

2303.15387 2023-03-28 cs.CV cs.GR 73%

Generalizable Neural Voxels for Fast Human Radiance Fields

Taoran Yi, Jiemin Fang, Xinggang Wang, Wenyu Liu

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

Comments Project page: http://taoranyi.com/gneuvox

2303.03966 2023-03-08 cs.CV cs.AI cs.GR cs.LG 73%

Semantic-aware Occlusion Filtering Neural Radiance Fields in the Wild

Jaewon Lee, Injae Kim, Hwan Heo, Hyunwoo J. Kim

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

Comments 11 pages, 5 figures

2211.14799 2022-11-29 cs.CV cs.GR cs.LG 73%

Sampling Neural Radiance Fields for Refractive Objects

Jen-I Pan, Jheng-Wei Su, Kai-Wen Hsiao, Ting-Yu Yen, Hung-Kuo Chu

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

Comments SIGGRAPH Asia 2022 Technical Communications. 4 pages, 4 figures, 1 table. Project: https://alexkeroro86.github.io/SampleNeRFRO/ Code: https://github.com/alexkeroro86/SampleNeRFRO

2211.12656 2022-11-24 cs.CV cs.RO 73%

ActiveRMAP: Radiance Field for Active Mapping And Planning

Huangying Zhan, Jiyang Zheng, Yi Xu, Ian Reid, Hamid Rezatofighi

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

Comments Under review

2210.04932 2022-10-12 cs.RO cs.AI cs.CV cs.LG 73%

NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields

Arunkumar Byravan, Jan Humplik, Leonard Hasenclever, Arthur Brussee, Francesco Nori, Tuomas Haarnoja, Ben Moran, Steven Bohez, Fereshteh Sadeghi, Bojan Vujatovic, Nicolas Heess

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

2209.05277 2022-09-13 cs.CV cs.GR 73%

StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints

Zheng Chen, Chen Wang, Yuan-Chen Guo, Song-Hai Zhang

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

2112.02308 2022-07-25 cs.CV cs.GR 73%

MoFaNeRF: Morphable Facial Neural Radiance Field

Yiyu Zhuang, Hao Zhu, Xusen Sun, Xun Cao

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

Comments accepted to ECCV2022; code available at http://github.com/zhuhao-nju/mofanerf

2206.11952 2022-06-27 cs.CV cs.GR 73%

UNeRF: Time and Memory Conscious U-Shaped Network for Training Neural Radiance Fields

Abiramy Kuganesan, Shih-yang Su, James J. Little, Helge Rhodin

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

2111.15234 2022-04-07 cs.CV cs.GR 73%

NeRFReN: Neural Radiance Fields with Reflections

Yuan-Chen Guo, Di Kang, Linchao Bao, Yu He, Song-Hai Zhang

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

Comments Accepted to CVPR 2022. Project page: https://bennyguo.github.io/nerfren/

2203.16626 2022-04-01 cs.CV cs.GR 73%

DDNeRF: Depth Distribution Neural Radiance Fields

David Dadon, Ohad Fried, Yacov Hel-Or

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

2203.11283 2022-03-23 cs.CV cs.GR 73%

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction

Xiaoshuai Zhang, Sai Bi, Kalyan Sunkavalli, Hao Su, Zexiang Xu

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

Comments CVPR 2022

2202.13162 2022-03-01 cs.CV cs.AI cs.GR cs.LG 73%

Pix2NeRF: Unsupervised Conditional $π$-GAN for Single Image to Neural Radiance Fields Translation

Shengqu Cai, Anton Obukhov, Dengxin Dai, Luc Van Gool

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

Comments 16 pages, 10 figures

2112.00724 2021-12-02 cs.CV cs.AI cs.GR 73%

RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs

Michael Niemeyer, Jonathan T. Barron, Ben Mildenhall, Mehdi S. M. Sajjadi, Andreas Geiger, Noha Radwan

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

Comments Project page available at https://m-niemeyer.github.io/regnerf/index.html

2404.09995 2024-11-14 cs.CV cs.AI cs.LG 72%

Taming Latent Diffusion Model for Neural Radiance Field Inpainting

Chieh Hubert Lin, Changil Kim, Jia-Bin Huang, Qinbo Li, Chih-Yao Ma, Johannes Kopf, Ming-Hsuan Yang, Hung-Yu Tseng

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

Comments Accepted to ECCV 2024. Project page: https://hubert0527.github.io/MALD-NeRF

2308.04413 2023-08-09 cs.CV 72%

Digging into Depth Priors for Outdoor Neural Radiance Fields

Chen Wang, Jiadai Sun, Lina Liu, Chenming Wu, Zhelun Shen, Dayan Wu, Yuchao Dai, Liangjun Zhang

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

Comments Accepted to ACM MM 2023. Project Page: https://cwchenwang.github.io/outdoor-nerf-depth

2111.15246 2022-05-31 cs.CV cs.AI 72%

Hallucinated Neural Radiance Fields in the Wild

Xingyu Chen, Qi Zhang, Xiaoyu Li, Yue Chen, Ying Feng, Xuan Wang, Jue Wang

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

Comments Accepted by CVPR 2022. Project website: https://rover-xingyu.github.io/Ha-NeRF/

2112.03288 2022-04-08 cs.CV 72%

Dense Depth Priors for Neural Radiance Fields from Sparse Input Views

Barbara Roessle, Jonathan T. Barron, Ben Mildenhall, Pratul P. Srinivasan, Matthias Nießner

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

Comments CVPR 2022, project page: https://barbararoessle.github.io/dense_depth_priors_nerf/ , video: https://youtu.be/zzkvvdcvksc

2608.12175 2026-08-13 cs.CV 新提交 70%

TGRHuman: Text-Guided Realistic 3D Human Generation via Diffusion Renderer

TGRHuman：基于扩散渲染器的文本引导逼真3D人体生成

Muxin Zhang, Chaohui Yu, Yuanwang Yang, Min Wei, Zhuo Su, Kun Li

机构 * Tianjin University（天津大学）

专题命中 NeRF ：NeRF(abstract,abstract_cn)；分类 cs.CV

AI总结本研究提出TGRHuman方法，解耦3D人体的几何与纹理生成，采用显式多视图优化结合扩散渲染器，实现高效高质量文本引导的逼真3D人体生成，性能优于现有方法。

2607.21485 2026-07-24 cs.CV 新提交 70%

Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation

用于高效高保真表示的循环正弦隐式神经表示

Hyunmin Cho, Jaejun Yoo, Kyong Hwan Jin

机构 * Department of Electrical Engineering, Korea University（韩国大学电气工程系）； Graduate School of Artificial Intelligence, UNIST（蔚山国立科学技术院人工智能研究生院）

专题命中 NeRF ：NeRF(abstract,abstract_cn)；分类 cs.CV

AI总结研究将正弦循环用于INRs谐波频谱丰富，通过共享正弦块迭代优化潜在表示，经实验验证其频谱行为，在图像和3D表示任务中表现出色，能以少参数和步骤实现高保真，还可迁移至多种相关任务。

Comments Accepted to ECCV 2026 (Poster)

2607.16287 2026-07-21 cs.CV cs.AI 新提交 70%

Identity-Consistent Expression Fields: A Disentangled Neural Radiance Field Framework for Few-Shot Facial Expression Synthesis

身份一致的表情场：用于少样本面部表情合成的解缠神经辐射场框架

Minh Tran

机构 * University of Science and Technology of Hanoi（河内科技大学）

专题命中 NeRF ：NeRF(abstract,abstract_cn)；分类 cs.CV

AI总结研究针对少样本面部表情合成问题，提出ICEF框架，将静态身份辐射分量与动态表情变形分量解缠，引入身份保留正则化器，纳入置信度加权条件特征扭曲步骤，提升新表情渲染质量与身份一致性。

2606.19718 2026-06-19 cs.CV 新提交 70%

One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model

基于3D先验引导扩散模型的单样本新视角与姿态人体图像合成

Shenjian Gong, Kangkan Wang, Shanshan Zhang, Jian Yang

机构 * PCA Lab, Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and Jiangsu Key Lab of Image and Video Understanding for Social Security, School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院教育部高维信息智能感知与系统重点实验室、江苏省社会安全图像与视频理解重点实验室及PCA实验室）； Advanced Laser Technology Laboratory of Anhui Province, Electronic Engineering Institute, National University of Defense Technology, and Jianghuai Advance Technology Center（国防科技大学电子工程学院安徽省先进激光技术实验室及江淮前沿技术中心）

专题命中 NeRF ：NeRF(abstract,abstract_cn)；分类 cs.CV

AI总结提出一种基于条件去噪扩散模型的方法，利用3D人体先验（法线图和颜色提示）作为几何和颜色条件，从单张参考图像合成任意姿态和视角的高质量人体图像，包括被遮挡部分。

Comments 30 pages, 10 figures

2606.02639 2026-06-03 eess.IV cs.AI cs.CV 70%

Sparse-View Lung Nodule Volumetry from Digitally Reconstructed Radiographs via AReT: Anatomy-Regularized TensoRF

通过AReT：解剖正则化TensoRF从数字重建放射图像进行稀疏视图肺结节体积测量

Spoorthi M, Suja Palaniswamy

机构 * Amrita University（阿姆里塔大学）

专题命中 NeRF ：NeRF(abstract,abstract_cn)；分类 cs.CV

AI总结本文发现并解决了TensoRF在X射线衰减场中的默认密度偏移问题，提出解剖正则化张量辐射场框架AReT，仅用三个正交X射线投影即可实现肺结节的稳定体积重建，在LIDC-IDRI数据集上达到高精度。

2605.18054 2026-05-19 eess.IV cs.CV cs.MM 70%

CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery

CATRF：用于体积分发的编码自适应三平面辐射场

Tung-I Chen, Lingdong Wang, Subhransu Maji, Ramesh K. Sitaraman

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）

专题命中 NeRF ：3DGS(abstract,abstract_cn)；分类 cs.CV

AI总结本文提出CATRF，一种用于体积分发的编码自适应三平面辐射场方法，通过在训练过程中将二维特征平面量化和打包到编码器友好的画布中，并利用标准编码器进行回程处理，从而在训练循环中插入非可微的编码器管道，使辐射场特征能够直接适应客户端侧的编码器失真，而无需引入任何学习的编码器参数。

2604.17965 2026-04-21 cs.CV 70%

MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene

MU-GeNeRF：多视角不确定性引导的可泛化神经辐射场用于干扰感知场景

Wenjie Mu, Zhan Li, Chuanzhou Su, Xuanyi Shen, Ziniu Liu, Fan Lu, Yujian Mo, Junqiao Zhao, Tiantian Feng, Chen Ye, Guang Chen

机构 * School of Computer Science and Technology, Tongji University, Shanghai, China（同济大学计算机科学与技术学院，上海，中国）； MOE Key Lab of Embedded System and Service Computing, Tongji University, Shanghai, China（同济大学嵌入式系统与服务计算MOE重点实验室，上海，中国）； College of Surveying and Geographic Informatics, Tongji University, Shanghai, China（同济大学测绘地理信息学院，上海，中国）

专题命中 NeRF ：NeRF(abstract,abstract_cn)；分类 cs.CV

AI总结本文提出MU-GeNeRF，通过多视角不确定性组件提升神经辐射场在存在瞬时干扰时的鲁棒性，实验表明其在场景重建中优于现有方法。

Comments Accepted by CVPR 2026

2604.16480 2026-04-21 cs.CV 70%

Positioning radiata pine branches requiring pruning by drone stereo vision

利用无人机立体视觉定位需修剪的辐射松枝位置

Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green

机构 * Centre of Data Science and Artificial Intelligence & School of Engineering and Computer Science（数据科学与人工智能中心及工程与计算机科学学院）

专题命中 NeRF ：NeRF(abstract,abstract_cn)；分类 cs.CV

AI总结本文提出基于无人机的立体视觉系统，用于检测和定位辐射松枝以支持自主修剪。通过比较不同模型在自定义数据集上的表现，验证了深度学习方法在低成本立体视觉中用于林业自动枝条定位的可行性。

2604.09639 2026-04-14 cs.CV 70%

3D Multi-View Stylization with Pose-Free Correspondences Matching for Robust 3D Geometry Preservation

基于姿态无关对应关系的3D多视角风格化

Shirsha Bose

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

AI总结本文提出一种无需姿态信息或显式3D表示的多视角风格化方法，通过复合目标结合外观迁移与几何保持，提升3D任务的鲁棒性。

1. NeRF 1354 篇

PERF: Panoramic Neural Radiance Field from a Single Panorama

ManifoldNeRF: View-dependent Image Feature Supervision for Few-shot Neural Radiance Fields

Locally Stylized Neural Radiance Fields

Improved Neural Radiance Fields Using Pseudo-depth and Fusion

Generalizable Neural Voxels for Fast Human Radiance Fields

Semantic-aware Occlusion Filtering Neural Radiance Fields in the Wild

Sampling Neural Radiance Fields for Refractive Objects

ActiveRMAP: Radiance Field for Active Mapping And Planning

NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields

StructNeRF: Neural Radiance Fields for Indoor Scenes with Structural Hints

MoFaNeRF: Morphable Facial Neural Radiance Field

UNeRF: Time and Memory Conscious U-Shaped Network for Training Neural Radiance Fields

NeRFReN: Neural Radiance Fields with Reflections

DDNeRF: Depth Distribution Neural Radiance Fields

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction

Pix2NeRF: Unsupervised Conditional $π$-GAN for Single Image to Neural Radiance Fields Translation

RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputs

Taming Latent Diffusion Model for Neural Radiance Field Inpainting

Digging into Depth Priors for Outdoor Neural Radiance Fields

Hallucinated Neural Radiance Fields in the Wild

Dense Depth Priors for Neural Radiance Fields from Sparse Input Views

TGRHuman: Text-Guided Realistic 3D Human Generation via Diffusion Renderer

Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation

Identity-Consistent Expression Fields: A Disentangled Neural Radiance Field Framework for Few-Shot Facial Expression Synthesis

One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model

Sparse-View Lung Nodule Volumetry from Digitally Reconstructed Radiographs via AReT: Anatomy-Regularized TensoRF

CATRF: Codec-Adaptive TriPlane Radiance Fields for Volumetric Content Delivery

MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene

Positioning radiata pine branches requiring pruning by drone stereo vision

3D Multi-View Stylization with Pose-Free Correspondences Matching for Robust 3D Geometry Preservation