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 19020 信号源:cs.CV, cs.GR, cs.RO

1. NeRF 1355 篇

2109.01847 2021-09-07 cs.CV 61%

Learning Object-Compositional Neural Radiance Field for Editable Scene Rendering

Bangbang Yang, Yinda Zhang, Yinghao Xu, Yijin Li, Han Zhou, Hujun Bao, Guofeng Zhang, Zhaopeng Cui

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

Comments Accepted to ICCV 2021. Project Page: https://zju3dv.github.io/object_nerf

详情

展开后加载摘要…

URL PDF HTML 收藏
2103.15875 2021-08-24 cs.CV 61%

In-Place Scene Labelling and Understanding with Implicit Scene Representation

Shuaifeng Zhi, Tristan Laidlow, Stefan Leutenegger, Andrew J. Davison

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

Comments Camera ready version. To be published in Proceedings of IEEE International Conference on Computer Vision (ICCV 2021) as Oral Presentation. Project page with more videos: https://shuaifengzhi.com/Semantic-NeRF/

详情

展开后加载摘要…

URL PDF HTML 收藏
2012.05903 2021-04-20 cs.CV 61%

Portrait Neural Radiance Fields from a Single Image

Chen Gao, Yichang Shih, Wei-Sheng Lai, Chia-Kai Liang, Jia-Bin Huang

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

Comments Project webpage: https://portrait-nerf.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.10174 2026-07-17 cs.CV 版本更新 57%

BathyFacto: Refraction-Aware Two-Media Neural Radiance Fields for Bathymetry

BathyFacto:考虑折射的双介质神经辐射场用于水深测量

Markus Brezovsky, Anatol Günthner, Frederik Schulte, Lukas Winiwarter, Boris Jutzi, Gottfried Mandlburger

机构 * Department of Geodesy and Geoinformation, TU Wien(维也纳技术大学测绘与地理信息系) Institute of Photogrammetry and Remote Sensing (IPF), Karlsruhe Institute of Technology (KIT)(卡尔斯鲁厄理工学院测绘与遥感研究所) Unit of Geometry and Surveying, University of Innsbruck(因斯布鲁克大学几何与测绘单位)

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

AI总结 BathyFacto通过整合Nerfacto,利用折射-aware的双介质神经辐射场技术,提高水下点云的测量精度,解决了水面折射带来的系统性深度偏差问题。

Comments 16 pages, 8 figures, 3 tables. Submitted to ISPRS Open Journal of Photogrammetry and Remote Sensing, Special Issue "3D Underwater Mapping from Above and Below"

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.27948 2026-07-13 cs.CV 版本更新 57%

RehearsalNeRF: Decoupling Intrinsic Neural Fields of Dynamic Illuminations for Scene Editing

RehearsalNeRF:解耦动态光照的内在神经场以实现场景编辑

Changyeon Won, Hyunjun Jung, Jungu Cho, Seonmi Park, Chi-Hoon Lee, Hae-Gon Jeon

机构 * Gwangju Institute of Science and Technology(光州科学技术院) Yonsei University(延世大学) CJ Corporation(CJ集团)

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

AI总结 RehearsalNeRF通过利用稳定光照下的场景数据,解耦动态光照下的场景辐射,提升动态光照下的视图合成和场景编辑性能。

Comments Accepted to the International Journal of Computer Vision (IJCV). Changyeon Won and Hyunjun Jung contributed equally to this work

详情

展开后加载摘要…

URL PDF HTML 收藏
2308.16041 2026-07-08 cs.CV 版本更新 57%

From Pixels to Portraits: A Comprehensive Survey of Talking Head Generation Techniques and Applications

从像素到肖像:会说话头像生成技术与应用的全面综述

Shreyank N Gowda, Dheeraj Pandey, Shashank Narayana Gowda

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 综述会说话头像生成技术,将文献分为四类方法并讨论其技术思想等。分析定量指标与感知质量差距,比较公开模型,研究新兴趋势,确定开放挑战,为从业者提供领域地图,突出相关技术和社会问题。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.23033 2026-07-07 cs.CV cs.NE 版本更新 57%

Adaptive Time-step Training for Enhancing Spike-Based Neural Radiance Fields

用于增强基于脉冲的神经辐射场的自适应时间步长训练

Ranxi Lin, Canming Yao, Jiayi Li, Weihang Liu, Xin Lou, Pingqiang Zhou

机构 * School of Information Science and Technology, ShanghaiTech University(信息科学与技术学院,上海科技大学) Guangdong Institute of Intelligence Science and Technology(广东智能科学与技术研究院)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 研究针对基于脉冲的神经辐射场模型固定推理时间步长效率低的问题,提出PATA框架,通过参数化目标推理时间步长并两阶段训练,结合多种策略降低推理成本并保持渲染质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18540 2026-06-10 cs.GR eess.IV 版本更新 57%

Real-time 3D Visualization of Radiance Fields on Light Field Displays

光场显示上辐射场的实时3D可视化

Jonghyun Kim, Cheng Sun, Michael Stengel, Matthew Chan, Andrew Russell, Jaehyun Jung, Wil Braithwaite, David Luebke, Shalini De Mello

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

AI总结 针对光场显示需要多视角高分辨率渲染而辐射场计算密集的问题,提出统一高效框架,通过共享中间扫描平面单次合成密集光场视图,实现实时渲染(200+ FPS),速度提升22倍。

Comments 19 pages, 14 figures. J. Kim, C. Sun, and M. Stengel contributed equally

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.26899 2026-04-30 eess.SY cs.RO cs.SY 57%

Safe Navigation using Neural Radiance Fields via Reachable Sets

通过可达集实现神经辐射场的安全导航

Omanshu Thapliyal, Malarvizhi Sankaranarayanasamy, Ravigopal Vennelakanti

机构 * Researcher, Hitachi America Ltd.(Hitachi America Ltd.研究人员) Sr. Researcher, Hitachi America Ltd.(Hitachi America Ltd.高级研究人员)

专题命中 NeRF :NeRF(abstract_cn);分类 cs.RO

AI总结 本文提出利用可达集和神经辐射场进行安全导航,通过约束最优控制解决路径规划问题,验证了在复杂环境中安全避障的能力。

Comments 5 pages, 8 figures, 2026 4th International Conference on Mechatronics, Control and Robotics (ICMCR)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.11931 2026-04-14 cs.CV 57%

Dark-EvGS: Event Camera as an Eye for Radiance Field in the Dark

暗光环境下的辐射场重建:事件相机作为视觉的眼睛

Jingqian Wu, Peiqi Duan, Zongqiang Wang, Changwei Wang, Boxin Shi, Edmund Y. Lam

机构 * Department of Electrical and Electronic Engineering, The University of Hong Kong(香港大学电机电子工程系) State Key Laboratory of Multimedia Information Processing and National Engineering Research Center of Visual Technology, School of Computer Science, Peking University(北京大学计算机学院多媒体信息处理国家重点实验室及视觉技术国家工程研究中心) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology(齐鲁工业大学(山东省科学院)山东省计算中心(国家超级计算济南中心)计算力网络与信息安全教育部重点实验室)

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

AI总结 本文提出Dark-EvGS框架,利用事件相机和3D高斯点绘制技术,在暗光环境中实现高质量辐射场重建,通过三重监督和颜色匹配模块提升合成图像质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.20654 2026-04-14 cs.CV cs.AI 57%

AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports

AccidentSim: 从真实世界事故报告生成具有物理真实碰撞轨迹的车辆碰撞视频

Xiangwen Zhang, Qian Zhang, Longfei Han, Qiang Qu, Xiaoming Chen, Weidong Cai

机构 * School of Computer and Artificial Intelligence, Beijing Technology and Business University(北京工商大学计算机与人工智能学院) The University of Sydney(悉尼大学)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 AccidentSim通过提取事故报告中的物理信息生成真实碰撞视频,结合物理模拟和NeRF技术提升视觉与物理真实性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.02836 2026-04-06 cs.CV 57%

Factorized Multi-Resolution HashGrid for Efficient Neural Radiance Fields: Execution on Edge-Devices

因子化多分辨率哈希网格:用于高效神经辐射场的执行边缘设备

Kim Jun-Seong, Mingyu Kim, GeonU Kim, Tae-Hyun Oh, Jin-Hwa Kim

机构 * POSTECH(浦项科技大学) KAIST(韩国科学技术院) NAVER AI Lab(NAVER AI实验室)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 本文提出Fact-Hash,一种用于边缘设备神经辐射场训练的参数编码方法,通过融合张量分解与哈希编码技术,提升内存效率和渲染速度,实现高质量3D表示。

Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L)

Journal ref IEEE Robotics and Automation Letters (RA-L), 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.19015 2026-03-17 cs.CV 57%

Simple-RF: Regularizing Sparse Input Radiance Fields with Simpler Solutions

Simple-RF: 通过更简单的解决方案正则化稀疏输入辐射场

Nagabhushan Somraj, Sai Harsha Mupparaju, Adithyan Karanayil, Rajiv Soundararajan

机构 * Indian Institute of Science(印度科学研究所)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 本文提出Simple-RF方法,通过设计增强模型和正则化框架,改进稀疏输入下辐射场的深度估计,从而在稀疏视图条件下实现更优的视图合成性能。

Comments The source code for our model can be found on our project page: https://nagabhushansn95.github.io/publications/2024/Simple-RF.html. Extension of arXiv:2309.03955

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.12078 2026-03-16 cs.CV 57%

Node-RF: Learning Generalized Continuous Space-Time Scene Dynamics with Neural ODE-based NeRFs

Node-RF:基于神经ODE的NeRF学习通用连续时空场景动态

Hiran Sarkar, Liming Kuang, Yordanka Velikova, Benjamin Busam

机构 * Technical University of Munich(慕尼黑技术大学) Munich Center for Machine Learning(慕尼黑机器学习中心)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 Node-RF通过结合神经ODE与动态NeRF,实现连续时间空间动态表示,能超越观测轨迹进行泛化。利用ODE求解器学习隐式场景状态,通过微分计算传播特征嵌入,实现长距离外推。

Comments Accepted to CVPR 2026. 13 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.03424 2026-03-16 cs.CV 57%

Weight Conditioning for Smooth Optimization of Neural Networks

权重条件化以实现神经网络的平滑优化

Hemanth Saratchandran, Thomas X. Wang, Simon Lucey

机构 * Australian Institute for Machine Learning, University of Adelaide(澳大利亚机器学习研究所,阿德莱德大学) Sorbonne Université, CNRS, ISIR(索邦大学,法国国家科学研究中心,ISIR)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 本文提出一种新的权重规范化技术,通过缩小权重矩阵的奇异值范围,提升矩阵条件数,从而改善梯度下降收敛性能,实验验证其在多种神经网络架构中的有效性。

Comments ECCV 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.05473 2026-03-06 cs.CV 57%

Towards 3D Scene Understanding of Gas Plumes in LWIR Hyperspectral Images Using Neural Radiance Fields

利用神经辐射场实现L波段超光谱图像中气体云三维场景理解

Scout Jarman, Zigfried Hampel-Arias, Adra Carr, Kevin R. Moon

机构 * Utah State University, Department of Mathematics & Statistics(犹他州立大学数学与统计学系) Los Alamos National Laboratory, Intelligence and Space Research Division(洛斯阿拉莫斯国家实验室情报与空间研究部)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 本文提出一种基于神经辐射场的三维场景重建方法,利用较少训练图像实现气体云检测,提升L波段超光谱图像中气体云的分析能力。

Comments This manuscript was submitted to SPIE JARS and is under review. Code and Data can be found at https://github.com/lanl/HSI-Nerfstudio and https://zenodo.org/records/18626884 respectively. Video 1 and Video 2 can be found at https://github.com/lanl/HSI-Nerfstudio/blob/main/renders/paper/grid_Falsecolor.mp4 and https://github.com/lanl/HSI-Nerfstudio/blob/main/renders/paper/grid_ACE.mp4 respectively

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21645 2026-02-26 cs.CV 57%

Lie Flow: Video Dynamic Fields Modeling and Predicting with Lie Algebra as Geometric Physics Principle

Lie Flow:基于李代数的视频动态场建模与预测:作为几何物理原理

Weidong Qiao, Wangmeng Zuo, Hui Li

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 LieFlow基于SE(3)李群建模视频动态场,通过统一几何空间学习平移和旋转,提升视点合成保真度与物理真实性。

Comments 10pages,5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.07986 2026-02-10 cs.CV 57%

Deepfake Synthesis vs. Detection: An Uneven Contest

深度伪造合成与检测:一场不平衡的竞赛

Md. Tarek Hasan, Sanjay Saha, Shaojing Fan, Swakkhar Shatabda, Terence Sim

机构 * United International University(国际大学) National University of Singapore(国立新加坡大学) BRAC University(布拉克大学)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 本研究发现现有深度伪造检测模型在面对现代合成技术生成的深度伪造时表现不佳,亟需改进以应对不断演变的生成技术。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.18849 2026-01-28 cs.CV 57%

Audio-Driven Talking Face Generation with Blink Embedding and Hash Grid Landmarks Encoding

基于眨眼嵌入和哈希网格地标编码的音频驱动说话人脸生成

Yuhui Zhang, Hui Yu, Wei Liang, Sunjie Zhang

机构 * Department of Control Science and Engineering, University of Shanghai for Science and Technology(控制科学与工程系,上海科学技术大学) School of Psychology and Neuroscience, University of Glasgow(心理学与神经科学学院,格拉斯哥大学)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 本文提出基于眨眼嵌入和哈希网格地标编码的音频驱动说话人脸生成方法,通过动态地标变换器和神经辐射场提升生成质量。

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.13861 2026-01-21 cs.CV 57%

PositionIC: Unified Position and Identity Consistency for Image Customization

PositionIC: 统一的位置和身份一致性用于图像定制

Junjie Hu, Tianyang Han, Kai Ma, Jialin Gao, Song Yang, Xianhua He, Junfeng Luo, Xiaoming Wei, Wenqiang Zhang

机构 * MeiGen AI Team, Meituan(美团MeiGen AI团队) Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan University(上海智能信息处理关键实验室,计算机科学与人工智能学院,复旦大学) College of Intelligent Robotics and Advanced Manufacturing, Fudan University(智能机器人与先进制造学院,复旦大学)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 PositionIC通过统一框架实现高保真、空间可控的多主体图像定制,引入BMPDS数据合成和可视化感知注意力机制,提升空间精度与身份一致性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.05250 2026-01-09 cs.CV 57%

QNeRF: Neural Radiance Fields on a Simulated Gate-Based Quantum Computer

QNeRF:在模拟的基于门的量子计算机上使用神经辐射场

Daniele Lizzio Bosco, Shuteng Wang, Giuseppe Serra, Vladislav Golyanik

机构 * Department of Mathematics, Computer Science and Physics, University of Udine(数学、计算机科学与物理系,乌迪内大学) Department of Biology, University of Naples Federico II(生物学系,那不勒斯费德里科二世大学) Max Planck Institute for Informatics, SIC, Saarbrücken, Germany(马克斯·普朗克信息研究所,萨尔布吕肯,德国)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

AI总结 QNeRF是一种基于量子计算的新型视角合成模型,利用量子电路编码空间和视点信息,实现更紧凑的模型和高效的3D表示学习。

Comments 30 pages, 15 figures, 11 tables; project page: https://4dqv.mpi-inf.mpg.de/QNeRF/

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20129 2025-12-29 cs.HC cs.CV 57%

Dreamcrafter: Immersive Editing of 3D Radiance Fields Through Flexible, Generative Inputs and Outputs

Dreamcrafter: 通过灵活、生成性输入和输出实现沉浸式3D辐射场编辑

Cyrus Vachha, Yixiao Kang, Zach Dive, Ashwat Chidambaram, Anik Gupta, Eunice Jun, Bjoern Hartmann

机构 * UC Berkeley(加州大学伯克利分校)

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

AI总结 Dreamcrafter通过灵活的生成式输入和输出,实现实时沉浸式3D辐射场编辑,结合模块化架构和多层级控制提升创作效率与沉浸感。

Comments CHI 2025, Project page: https://dream-crafter.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18293 2025-11-25 cs.RO 57%

AIA-UltraNeRF:Acoustic-Impedance-Aware Neural Radiance Field with Hash Encodings for Robotic Ultrasound Reconstruction and Localization

AIA-UltraNeRF:具有哈希编码的声学阻抗感知神经辐射场用于机器人超声重建与定位

Shuai Zhang, Jingsong Mu, Cancan Zhao, Leiqi Tian, Zhijun Xing, Bo Ouyang, Xiang Li

机构 * School of Management, Hefei University of Technology(合肥工业大学管理学院) First Affiliated Hospital of University of Science and Technology of China(中国科学技术大学第一附属医院) Department of Ultrasound Diagnosis, the Second Xiangya Hospital of Central South University(中南大学湘雅医学院第二医院超声诊断科) Intelligent Ultrasound Division of VINNO Technology Co., Ltd.(VINNO技术有限公司智能超声事业部) Department of Automation, Tsinghua University(清华大学自动化系)

专题命中 NeRF :NeRF(abstract);分类 cs.RO

AI总结 AIA-UltraNeRF通过引入声学阻抗感知和哈希编码技术,提升机器人超声重建与定位的效率和准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.02510 2025-11-05 cs.CV 57%

LiteVoxel: Low-memory Intelligent Thresholding for Efficient Voxel Rasterization

Jee Won Lee, Jongseong Brad Choi

机构 * State University of New York(纽约州立大学)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.12836 2025-09-17 cs.CV 57%

Exploring Metric Fusion for Evaluation of NeRFs

Shreyas Shivakumara, Gabriel Eilertsen, Karljohan Lundin Palmerius

机构 * Department of Science and Technology(科学与技术系) Linköping University(林雪平大学)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

Comments Accepted for 17th International Conference on Quality of Multimedia Experience (QoMEX 25)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.00626 2025-08-29 cs.CV 57%

ZIM: Zero-Shot Image Matting for Anything

Beomyoung Kim, Chanyong Shin, Joonhyun Jeong, Hyungsik Jung, Se-Yun Lee, Sewhan Chun, Dong-Hyun Hwang, Joonsang Yu

机构 * NAVER Cloud, ImageVision(NAVER云,ImageVision)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

Comments ICCV 2025 (Highlight)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.19903 2025-08-27 cs.CV cs.LG 57%

Incremental Multi-Scene Modeling via Continual Neural Graphics Primitives

Prajwal Singh, Ashish Tiwari, Gautam Vashishtha, Shanmuganathan Raman

机构 * CVIG Lab IIT Gandhinagar Gujarat, India(IIT Gandhinagar 研究所)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.02005 2025-08-26 cs.CV 57%

Learning Heterogeneous Mixture of Scene Experts for Large-scale Neural Radiance Fields

Zhenxing Mi, Ping Yin, Xue Xiao, Dan Xu

机构 * Department of Computer Science and Engineering, The Hong Kong University of Science and Technology(计算机科学与工程系,香港科学与技术大学) Inspur Cloud Information Technology Co, Ltd(Inspur云信息技术有限公司)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

Comments Accepted by TPAMI

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.12163 2025-08-19 cs.CV cs.AI cs.HC cs.LG 57%

RealTalk: Realistic Emotion-Aware Lifelike Talking-Head Synthesis

Wenqing Wang, Yun Fu

机构 * Northeastern University(东北大学)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

Comments Accepted to the ICCV 2025 Workshop on Artificial Social Intelligence

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.08798 2025-08-13 cs.CV 57%

MonoPartNeRF:Human Reconstruction from Monocular Video via Part-Based Neural Radiance Fields

Yao Lu, Jiawei Li, Ming Jiang

机构 * The School of Computer Science and Information Security, Guilin University of Electronic Technology(桂林电子科技大学计算机科学与信息安全学院) Metaverse Application Engineering Center(元宇宙应用工程中心)

专题命中 NeRF :NeRF(abstract);分类 cs.CV

详情

展开后加载摘要…

URL PDF HTML 收藏