3D 视觉 - arXivDaily 专题

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。

2602.23574 2026-04-01 cs.CV cs.AI cs.LG 70%

Evidential Neural Radiance Fields

可信神经辐射场

Ruxiao Duan, Alex Wong

机构 * Yale University（耶鲁大学）

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

AI总结本文提出可信神经辐射场，通过单次前向传递直接量化aleatoric和epistemic不确定性，提升三维场景建模的可靠性与精度。

Comments The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026

2603.25008 2026-03-31 cs.CV cs.AI 70%

Few TensoRF: Enhance the Few-shot on Tensorial Radiance Fields

Few TensoRF: 提升张量辐射场的少样本重建

Thanh-Hai Le, Hoang-Hau Tran, Trong-Nghia Vu

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

AI总结 Few TensoRF结合TensorRF的高效张量表示与FreeNeRF的频率驱动少样本正则化，通过加速渲染并引入频率和遮挡掩膜，提升稀疏输入视角下的稳定性与重建质量，实验表明其在Synthesis NeRF基准上PSNR提升显著。

Comments 11 pages, 8 figures

2603.20128 2026-03-23 cs.CV 70%

Generalizable NGP-SR: Generalizable Neural Radiance Fields Super-Resolution via Neural Graph Primitives

可推广的NGP-SR：通过神经图形原语实现可推广的神经辐射场超分辨率

Wanqi Yuan, Omkar Sharad Mayekar, Connor Pennington, Nianyi Li

机构 * Clemson University（克莱姆森大学）

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

AI总结本文提出一种3D感知的超分辨率框架，直接从低分辨率图像重建高分辨率辐射场，无需外部参考或后处理，提升重建质量和运行效率。

2406.17438 2026-03-04 cs.CV 70%

Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes

隐式动物园：一个大规模神经隐式函数数据集，用于2D图像和3D场景

Qi Ma, Danda Pani Paudel, Ender Konukoglu, Luc Van Gool

机构 * Computer Vision Lab, ETH Zurich（苏黎世联邦理工学院计算机视觉实验室）； INSAIT, Sofia University（索菲亚大学INSAIT）

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

AI总结隐式动物园是一个大规模神经隐式函数数据集，用于2D图像和3D场景，通过提供高质量数据促进研究，提升图像分类、语义分割和3D姿态回归性能。

2602.15775 2026-02-18 cs.CV 70%

NeRFscopy: Neural Radiance Fields for in-vivo Time-Varying Tissues from Endoscopy

NeRFscopy：基于神经辐射场的内窥镜时间变化组织的3D重建

Laura Salort-Benejam, Antonio Agudo

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

AI总结 NeRFscopy通过神经辐射场技术，从单目内窥镜视频中实现可变形组织的3D重建和新视角合成，无需模板或预训练模型。

Comments ISBI 2026

2601.01431 2026-01-06 cs.CV 70%

EdgeNeRF: Edge-Guided Regularization for Neural Radiance Fields from Sparse Views

EdgeNeRF: 基于边缘引导的神经辐射场从稀疏视角进行3D重建

Weiqi Yu, Yiyang Yao, Lin He, Jianming Lv

机构 * School of Computer Science（计算机科学学院）； South China University of Technology（华南理工大学）； Technology（技术）； Guangzhou, China（中国广州）

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

AI总结 EdgeNeRF通过边缘引导的深度正则化方法，提升稀疏视角下3D重建的几何边界精度与质量。

Comments PRCV 2025

2503.07828 2025-12-04 cs.CV 70%

Neural Radiance and Gaze Fields for Visual Attention Modeling in 3D Environments

神经辐射与注视场用于3D环境中的视觉注意建模

Andrei Chubarau, Yinan Wang, James J. Clark

机构 * McGill University Centre for Intelligent Machines（麦吉尔大学智能机器中心）

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

AI总结 NeRGs通过神经辐射场和注视场结合，实现对3D环境中视觉注意的建模与可视化，支持交互式帧率下的注视场显示并有效处理遮挡问题。

Comments 11 pages, 8 figures

2511.06408 2025-11-11 cs.CV 70%

VDNeRF: Vision-only Dynamic Neural Radiance Field for Urban Scenes

Zhengyu Zou, Jingfeng Li, Hao Li, Xiaolei Hou, Jinwen Hu, Jingkun Chen, Lechao Cheng, Dingwen Zhang

机构 * Northwestern Polytechnical University（西北工业大学）； University of Oxford（牛津大学）； Hefei University Of Technology（合肥工业大学）

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

2510.19371 2025-10-23 cs.CV 70%

AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields

Woo Jae Kim, Kyu Beom Han, Yoonki Cho, Youngju Na, Junsik Jung, Sooel Son, Sung-eui Yoon

机构 * School of Computing, Korea Advanced Institute of Science and Technology (KAIST)（计算学院，韩国科学技术院（KAIST））

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

Comments BMVC 2025

2510.00592 2025-10-02 cs.CV 70%

Multi-level Dynamic Style Transfer for NeRFs

Zesheng Li, Shuaibo Li, Wei Ma, Jianwei Guo, Hongbin Zha

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

Comments Accepted by Computational Visual Media Journal (CVMJ)

2509.15123 2025-09-22 cs.CV 70%

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

Fang Li, Hao Zhang, Narendra Ahuja

机构 * University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

Comments NeurIPS 2025 Spotlight

2508.16932 2025-08-26 cs.CV 70%

Align 3D Representation and Text Embedding for 3D Content Personalization

Qi Song, Ziyuan Luo, Ka Chun Cheung, Simon See, Renjie Wan

机构 * Department of Computer Science（计算机科学系）； Hong Kong Baptist University（香港 Baptist 大学）； NVIDIA AI Technology Center（NVIDIA AI 技术中心）； NVIDIA

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

2304.12294 2025-08-25 cs.CV 70%

Explicit Correspondence Matching for Generalizable Neural Radiance Fields

Yuedong Chen, Haofei Xu, Qianyi Wu, Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai

机构 * Monash University（墨尔本大学）； ETH Zurich（苏黎世联邦理工学院）； University of Oxford（牛津大学）； Nanyang Technological University（南洋理工大学）

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

Comments TPAMI 2025, Project page: https://donydchen.github.io/matchnerf, Code: https://github.com/donydchen/matchnerf

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025

2505.16912 2025-07-31 cs.RO 70%

UAV See, UGV Do: Aerial Imagery and Virtual Teach Enabling Zero-Shot Ground Vehicle Repeat

Desiree Fisker, Alexander Krawciw, Sven Lilge, Melissa Greeff, Timothy D. Barfoot

机构 * University of Toronto Robotics Institute（多伦多大学机器人研究所）； University of Toronto Institute of Aerospace Studies（多伦多大学航空航天研究学院）； Ingenuity Labs（Ingenuity实验室）； Department of Electrical and Computer Engineering（电气与计算机工程系）

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

Comments 8 pages, 8 figures, accepted to IROS 2025

2507.20110 2025-07-29 cs.CV cs.AI cs.LG 70%

NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding

Shiyu Liu, Lianlei Shan

机构 * School of Electrical and Electronic Engineering（电气与电子工程学院）； Nanyang Technological University（南洋理工大学）； School of Computer Science and Technology（计算机科学与技术学院）； University of Chinese Academy of Sciences（中国科学院大学）

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

Comments **14 pages, 3 figures, 2 tables

2507.17351 2025-07-24 cs.CV 70%

Exploring Active Learning for Label-Efficient Training of Semantic Neural Radiance Field

Yuzhe Zhu, Lile Cai, Kangkang Lu, Fayao Liu, Xulei Yang

机构 * Institute for Infocomm Research (I 2 R), A*STAR, Singapore（信息通信研究所（I 2 R），A*STAR，新加坡）； Nanyang Technological University, Singapore（南洋理工大学，新加坡）

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

Comments Accepted to ICME 2025

2507.07519 2025-07-11 cs.CV 70%

MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation

Bangning Wei, Joshua Maraval, Meriem Outtas, Kidiyo Kpalma, Nicolas Ramin, Lu Zhang

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

2507.04408 2025-07-08 cs.CV 70%

A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields

Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Pascal Fua

机构 * Computer Vision Laboratory, EPFL, Switzerland（瑞士联邦理工学院计算机视觉实验室）

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

Comments ICCV 2025 accepted

2507.00969 2025-07-02 cs.CV cs.AI 70%

Surgical Neural Radiance Fields from One Image

Alberto Neri, Maximilan Fehrentz, Veronica Penza, Leonardo S. Mattos, Nazim Haouchine

机构 * Biomedical Robotics Lab, Advanced Robotics（生物医学机器人实验室，先进机器人技术）； Istituto Italiano di Tecnologia（意大利技术研究所）； Department of Computer Science, Bioengineering, Robotics and Systems Engineering (DIBRIS)（计算机科学、生物工程、机器人与系统工程系（DIBRIS））； University of Genoa（热那亚大学）； Technical University of Munich（慕尼黑技术大学）； Harvard Medical School, Brigham and Women’s Hospital（哈佛医学院，布里洛妇女医院）

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

Journal ref Int J CARS (2025)

2312.13528 2025-06-04 cs.CV 70%

MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video

Minh-Quan Viet Bui, Jongmin Park, Jihyong Oh, Munchurl Kim

机构 * School of Electrical Engineering, Korea Advanced Institute of Science and Technology（韩国科学技术院电子工程学院）； Department of Imaging Science, GSAIM, Chung-Ang University（Chung-Ang大学成像科学系）

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

Comments Accepted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. The first two authors contributed equally to this work (equal contribution). The last two authors are co-corresponding authors. Please visit our project page at https://kaist-viclab.github.io/moblurf-site/

2505.19793 2025-05-27 cs.CV 70%

Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction

Li Fang, Hao Zhu, Longlong Chen, Fei Hu, Long Ye, Zhan Ma

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

Comments CVPR 2025

2505.06894 2025-05-13 cs.CV cs.AI cs.LG cs.NE 70%

NeuGen: Amplifying the 'Neural' in Neural Radiance Fields for Domain Generalization

Ahmed Qazi, Abdul Basit, Asim Iqbal

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

Comments 18 pages, 6 figures

2505.06638 2025-05-13 cs.RO 70%

3D Characterization of Smoke Plume Dispersion Using Multi-View Drone Swarm

Nikil Krishnakumar, Shashank Sharma, Srijan Kumar Pal, Jiarong Hong

机构 * Minnesota Robotics Institute, St. Anthony Falls Laboratory, University of Minnesota（明尼苏达机器人研究所、圣安东尼瀑布实验室、明尼苏达大学）

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

Comments 10 pages, 8 figures

2410.09049 2025-05-09 cs.CV 70%

SceneCraft: Layout-Guided 3D Scene Generation

Xiuyu Yang, Yunze Man, Jun-Kun Chen, Yu-Xiong Wang

机构 * Shanghai Jiao Tong University（上海交通大学）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

Comments NeurIPS 2024. Code: https://github.com/OrangeSodahub/SceneCraft Project Page: https://orangesodahub.github.io/SceneCraft

2405.19876 2025-04-21 cs.CV 70%

IReNe: Instant Recoloring of Neural Radiance Fields

Alessio Mazzucchelli, Adrian Garcia-Garcia, Elena Garces, Fernando Rivas-Manzaneque, Francesc Moreno-Noguer, Adrian Penate-Sanchez

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

2503.15070 2025-03-20 cs.CV 70%

MultiBARF: Integrating Imagery of Different Wavelength Regions by Using Neural Radiance Fields

Kana Kurata, Hitoshi Niigaki, Xiaojun Wu, Ryuichi Tanida

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

2503.13710 2025-03-19 cs.CV 70%

Improving Geometric Consistency for 360-Degree Neural Radiance Fields in Indoor Scenarios

Iryna Repinetska, Anna Hilsmann, Peter Eisert

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

Journal ref Proc. VISAPP 2025

2503.12086 2025-03-18 cs.CV 70%

FA-BARF: Frequency Adapted Bundle-Adjusting Neural Radiance Fields

Rui Qian, Chenyangguang Zhang, Yan Di, Guangyao Zhai, Ruida Zhang, Jiayu Guo, Benjamin Busam, Jian Pu

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

2406.12202 2025-03-17 cs.RO 70%

Fast Global Localization on Neural Radiance Field

Mangyu Kong, Seongwon Lee, Jaewon Lee, Euntai Kim

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

Comments Accepted at ICRA 2025

1. NeRF 1355 篇

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

Evidential Neural Radiance Fields

Few TensoRF: Enhance the Few-shot on Tensorial Radiance Fields

Generalizable NGP-SR: Generalizable Neural Radiance Fields Super-Resolution via Neural Graph Primitives

Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes

NeRFscopy: Neural Radiance Fields for in-vivo Time-Varying Tissues from Endoscopy

EdgeNeRF: Edge-Guided Regularization for Neural Radiance Fields from Sparse Views

Neural Radiance and Gaze Fields for Visual Attention Modeling in 3D Environments

VDNeRF: Vision-only Dynamic Neural Radiance Field for Urban Scenes

AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields

Multi-level Dynamic Style Transfer for NeRFs

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

Align 3D Representation and Text Embedding for 3D Content Personalization

Explicit Correspondence Matching for Generalizable Neural Radiance Fields

UAV See, UGV Do: Aerial Imagery and Virtual Teach Enabling Zero-Shot Ground Vehicle Repeat

NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding

Exploring Active Learning for Label-Efficient Training of Semantic Neural Radiance Field

MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation

A View-consistent Sampling Method for Regularized Training of Neural Radiance Fields

Surgical Neural Radiance Fields from One Image

MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video

Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction

NeuGen: Amplifying the 'Neural' in Neural Radiance Fields for Domain Generalization

3D Characterization of Smoke Plume Dispersion Using Multi-View Drone Swarm

SceneCraft: Layout-Guided 3D Scene Generation

IReNe: Instant Recoloring of Neural Radiance Fields

MultiBARF: Integrating Imagery of Different Wavelength Regions by Using Neural Radiance Fields

Improving Geometric Consistency for 360-Degree Neural Radiance Fields in Indoor Scenarios

FA-BARF: Frequency Adapted Bundle-Adjusting Neural Radiance Fields

Fast Global Localization on Neural Radiance Field