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 19032 信号源:cs.CV, cs.GR, cs.RO

1. Gaussian Splatting 3141 篇

2405.15125 2024-10-29 cs.CV 91%

HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting

Yuanhao Cai, Zihao Xiao, Yixun Liang, Minghan Qin, Yulun Zhang, Xiaokang Yang, Yaoyao Liu, Alan Yuille

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);novel view synthesis(title,abstract);NeRF(abstract);point cloud(abstract)

Comments NeurIPS 2024; The first 3D Gaussian Splatting-based method for HDR imaging

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.05218 2026-08-07 cs.AI cs.SD 新提交 90%

PD-GS: Phoneme-Driven 3DGS for Audio-Driven Talking Heads

PD-GS:音素驱动的3DGS用于音频驱动的说话头生成

Ao Fu, Yi Zhou

机构 * Southeast University(东南大学) School of Computer Science and Engineering(计算机科学与工程学院)

专题命中 Gaussian Splatting :3DGS(title,title_cn);Gaussian Splatting(abstract)

AI总结 针对3DGS说话头渲染的漏嘴伪影问题,提出PD-GS模型,通过LFM融合音频与音素信息,在HDTF数据集上实现最优嘴唇几何,提升神经化身的语言忠实度。

Comments Accepted to ACM MM 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.16211 2026-03-18 cs.CV 90%

Leveling3D: Leveling Up 3D Reconstruction with Feed-Forward 3D Gaussian Splatting and Geometry-Aware Generation

Leveling3D: 通过前馈3D高斯点划法与几何感知生成提升3D重建

Yiming Huang, Baixiang Huang, Beilei Cui, Chi Kit Ng, Long Bai, Hongliang Ren

机构 * The Chinese University of Hong Kong(香港中文大学)

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);3D reconstruction(title,abstract);3D vision(abstract);3DGS(abstract)

AI总结 Leveling3D结合前馈3D重建与几何一致生成,解决传统方法在 extrapolated view 中的缺失区域问题,通过几何感知适配器提升3D重建质量,实现生成与重建的同步优化。

Comments 26 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13011 2025-11-18 cs.CV 90%

Beyond Darkness: Thermal-Supervised 3D Gaussian Splatting for Low-Light Novel View Synthesis

Qingsen Ma, Chen Zou, Dianyun Wang, Jia Wang, Liuyu Xiang, Zhaofeng He

机构 * Beijing University of Posts and Telecommunications(北京邮电大学)

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);novel view synthesis(title,abstract);3DGS(abstract);3D reconstruction(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15457 2025-08-22 cs.CV 90%

Enhancing Novel View Synthesis from extremely sparse views with SfM-free 3D Gaussian Splatting Framework

Zongqi He, Hanmin Li, Kin-Chung Chan, Yushen Zuo, Hao Xie, Zhe Xiao, Jun Xiao, Kin-Man Lam

机构 * Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University(电子与电气工程系,香港理工大学) School of Intelligent Systems Engineering, Sun Yat-sen University(智能系统工程学院,中山大学)

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);novel view synthesis(title,abstract);3DGS(abstract);point cloud(abstract)

Comments 13 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19854 2025-05-30 cs.CV 90%

Sparse2DGS: Sparse-View Surface Reconstruction using 2D Gaussian Splatting with Dense Point Cloud

Natsuki Takama, Shintaro Ito, Koichi Ito, Hwann-Tzong Chen, Takafumi Aoki

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);point cloud(title,abstract);3D reconstruction(abstract);novel view synthesis(abstract)

Comments Accepted to ICIP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.09129 2025-04-15 cs.CV 90%

A Constrained Optimization Approach for Gaussian Splatting from Coarsely-posed Images and Noisy Lidar Point Clouds

Jizong Peng, Tze Ho Elden Tse, Kai Xu, Wenchao Gao, Angela Yao

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);point cloud(title,abstract);3DGS(abstract);3D reconstruction(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.01042 2025-04-02 cs.CV 90%

Self-Calibrating 4D Novel View Synthesis from Monocular Videos Using Gaussian Splatting

Fang Li, Hao Zhang, Narendra Ahuja

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);novel view synthesis(title,abstract);NeRF(abstract);point cloud(abstract)

Comments GitHub Page: https://github.com/fangli333/SC-4DGS

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.16964 2025-03-24 cs.CV 90%

DroneSplat: 3D Gaussian Splatting for Robust 3D Reconstruction from In-the-Wild Drone Imagery

Jiadong Tang, Yu Gao, Dianyi Yang, Liqi Yan, Yufeng Yue, Yi Yang

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);3D reconstruction(title,abstract);NeRF(abstract);3DGS(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.03637 2024-11-07 cs.CV 90%

Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis

Rui Peng, Wangze Xu, Luyang Tang, Liwei Liao, Jianbo Jiao, Ronggang Wang

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);novel view synthesis(title,abstract);NeRF(abstract);3DGS(abstract)

Comments NeurIPS 2024 Accepted

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.13943 2024-10-30 cs.CV 90%

DOGS: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus

Yu Chen, Gim Hee Lee

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);3D reconstruction(title);NeRF(abstract);3DGS(abstract)

Comments Accepted to NeurIPS 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.18784 2024-05-30 cs.CV 90%

LP-3DGS: Learning to Prune 3D Gaussian Splatting

Zhaoliang Zhang, Tianchen Song, Yongjae Lee, Li Yang, Cheng Peng, Rama Chellappa, Deliang Fan

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);3DGS(title,abstract);point cloud(abstract);novel view synthesis(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.18795 2024-05-28 cs.CV cs.AI 90%

Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstruction

Qiuhong Shen, Zike Wu, Xuanyu Yi, Pan Zhou, Hanwang Zhang, Shuicheng Yan, Xinchao Wang

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);3D reconstruction(title,abstract);3DGS(abstract);point cloud(abstract)

Comments project page: https://florinshen.github.io/gamba-project

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.19706 2024-05-10 cs.CV 90%

RTG-SLAM: Real-time 3D Reconstruction at Scale using Gaussian Splatting

Zhexi Peng, Tianjia Shao, Yong Liu, Jingke Zhou, Yin Yang, Jingdong Wang, Kun Zhou

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);3D reconstruction(title,abstract);NeRF(abstract);novel view synthesis(abstract)

Comments To be published in ACM SIGGRAPH 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.03203 2024-04-09 cs.CV 90%

Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields

Shijie Zhou, Haoran Chang, Sicheng Jiang, Zhiwen Fan, Zehao Zhu, Dejia Xu, Pradyumna Chari, Suya You, Zhangyang Wang, Achuta Kadambi

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);3DGS(title,abstract);NeRF(abstract);novel view synthesis(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.00931 2026-08-04 cs.RO cs.CV 新提交 90%

Stipple: Real-Time Incremental Gaussian Splatting with Visual-Inertial Tracking

Stipple:基于视觉-惯性跟踪的实时增量高斯溅射技术

Kilian Northoff, Mateo de Mayo, Daniel Cremers

机构 * Technical University of Munich(慕尼黑工业大学) Munich Center for Machine Learning(慕尼黑机器学习中心)

专题命中 Gaussian Splatting :3DGS(summary_cn,abstract);Gaussian Splatting(title,abstract);3D reconstruction(abstract);分类 cs.CV、cs.RO

AI总结 本文提出Stipple方法,结合Basalt视觉-惯性跟踪系统与Brush增量3D高斯溅射技术,实现实时同步跟踪重建,替代3DGS繁重步骤,为机器人与XR的实时3D重建提供解决方案。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21898 2026-06-23 cs.GR cs.CV 新提交 90%

Mesh2GS: White-Box 3DGS Construction via Plenoptic Sampling

Mesh2GS: 通过全光采样实现白盒3DGS构建

Haoran Zhu, Youcheng Cai, Huangsheng Du, Jingyang Meng, Ligang Liu

机构 * University of Science and Technology of China(中国科学技术大学)

专题命中 Gaussian Splatting :3DGS(title,title_cn);Gaussian Splatting(abstract);3D reconstruction(abstract);分类 cs.CV、cs.GR

AI总结 提出Mesh2GS框架,基于全光采样理论从网格几何直接生成3D高斯,实现奈奎斯特级全局光照渲染,并通过反照率-明暗分解和神经照明增强模块处理非朗伯效应。

Comments 16 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.02172 2026-06-23 cs.CV cs.GR cs.LG 90%

SplatSuRe: Selective Super-Resolution for Multi-view Consistent 3D Gaussian Splatting

SplatSuRe:多视角一致3D高斯点溅的选择性超分辨率

Pranav Asthana, Alex Hanson, Allen Tu, Tom Goldstein, Matthias Zwicker, Amitabh Varshney

机构 * University of Maryland, College Park(马里兰大学 College Park分校)

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);NeRF(abstract,abstract_cn);3DGS(abstract,abstract_cn);novel view synthesis(abstract)

AI总结 SplatSuRe通过选择性超分辨率技术,在多视角一致的3D高斯点溅中提升渲染质量,通过相机姿态与场景几何关系指导超分辨率内容的添加,提升局部前景细节的清晰度和一致性。

Comments Project Page: https://splatsure.github.io/

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.18544 2026-06-03 cs.CV cs.GR 90%

GS-ROR$^2$: Bidirectional-guided 3DGS and SDF for Reflective Object Relighting and Reconstruction

GS-ROR$^2$: 双向引导的3DGS和SDF用于反射物体重光照与重建

Zuo-Liang Zhu, Beibei Wang, Jian Yang

机构 * VCIP, College of Computer Science, Nankai University(VCIP,计算机科学学院,南开大学) School of Intelligence Science and Technology, Nanjing University(智能科学与技术学校,南京大学)

专题命中 Gaussian Splatting :3DGS(title,title_cn);Gaussian Splatting(abstract);novel view synthesis(abstract);分类 cs.CV、cs.GR

AI总结 提出一种双向引导框架,通过SDF辅助的高斯溅射优化重光照模型,并利用GS引导的SDF增强实现高质量几何重建,解决反射物体重光照与重建中的几何约束和细节捕捉问题。

Comments Accepted by ACM TOG

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.09977 2026-06-16 cs.CV 版本更新 90%

A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation

3D高斯泼溅应用综述:分割、编辑与生成

Shuting He, Peilin Ji, Yitong Yang, Changshuo Wang, Jiayi Ji, Yinglin Wang, Henghui Ding

机构 * Shanghai University of Finance and Economics(上海财经大学) University College London(伦敦大学学院) Xiamen University(厦门大学) Fudan University(复旦大学)

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);3DGS(abstract,abstract_cn);NeRF(abstract,abstract_cn);novel view synthesis(abstract)

AI总结 综述3D高斯泼溅在分割、编辑和生成三大任务中的应用,总结代表性方法、监督策略和学习范式,并分析公共基准上的比较结果。

Comments IEEE TPAMI, GitHub Repo: https://github.com/heshuting555/Awesome-3DGS-Applications

Journal ref IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.21629 2025-07-01 cs.GR cs.CV 90%

ICP-3DGS: SfM-free 3D Gaussian Splatting for Large-scale Unbounded Scenes

Chenhao Zhang, Yezhi Shen, Fengqing Zhu

机构 * Elmore Family School of Electrical and Computer Engineering(电气与计算机工程学院) Purdue University(普渡大学)

专题命中 Gaussian Splatting :3DGS(title,abstract);Gaussian Splatting(title,abstract);novel view synthesis(abstract);分类 cs.CV、cs.GR

Comments 6 pages, Source code is available at https://github.com/Chenhao-Z/ICP-3DGS. To appear at ICIP 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.07144 2026-08-10 cs.CV 新提交 90%

InstanceSplat: Instance-Aware Feed-Forward 3D Gaussian Splatting for Scene Understanding

InstanceSplat:面向场景理解的实例感知前馈三维高斯溅射

Minchao Jiang, Xiaoxuan Ma, Shunyu Jia, Haoru Wang, Zhang Liang, Wentao Zhu

专题命中 Gaussian Splatting :3DGS(summary_cn,abstract);Gaussian Splatting(title,abstract);3D reconstruction(abstract);分类 cs.CV

AI总结 InstanceSplat是统一前馈3DGS框架,通过单次前向传播构建联合编码多信息的实例感知高斯表示,以实例为中心的学习策略实现重建与场景理解互益,在多任务上达到SOTA性能与强泛化性。

Comments Project page: https://jamchaos.github.io/InsSplat/

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.03279 2026-08-05 cs.CV 新提交 90%

3DGSI-Assessor: A Large-Scale Dataset and An LMM-based Method for 3D Gaussian Splatting Image Quality Assessment

3DGSI-Assessor:面向3D高斯溅射图像质量评估的大规模数据集与基于大视觉语言模型的方法

Yuke Xing, Jiarui Wang, William Gordon, Zhu Li, Guangtao Zhai, Yiling Xu

专题命中 Gaussian Splatting :3DGS(summary_cn,abstract);Gaussian Splatting(title,abstract);novel view synthesis(abstract);分类 cs.CV

AI总结 针对3D高斯溅射压缩的失真评估缺口,提出含15200张图像的多维IQA数据集3DGS-IEval-15K+,并构建基于大视觉语言模型的一体化IQA框架3DGSI-Assessor,该框架在对应数据集上达SOTA且泛化性良好。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.13524 2026-07-16 cs.RO 新提交 90%

COLMAR: Cooperative View Policy Learning for Multi-Agent Active 3D Reconstruction

COLMAR:用于多智能体主动3D重建的协作视图策略学习

Phu Pham, Damon Conover, Aniket Bera

机构 * Purdue University(普渡大学) DEVCOM Army Research Laboratory(陆军研究实验室)

专题命中 Gaussian Splatting :3DGS(summary_cn,abstract);3D reconstruction(title,abstract);Gaussian Splatting(abstract);分类 cs.RO

AI总结 研究多智能体主动3D重建中协调效率低的问题,提出COLMAR框架,将视点分配作为共享策略优化,用参数共享PPO训练,结合3DGS重建,实验表明相比基线在传感预算匹配时重建精度和覆盖率显著提升。

Comments 8 pages, 5 figures, IROS 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.14316 2026-07-14 cs.CV 版本更新 90%

Direct Object-Level Reconstruction via Probabilistic Gaussian Splatting

通过概率高斯溅射实现直接的对象级重建

Shuai Guo, Ao Guo, Junchao Zhao, Qi Chen, Yuxiang Qi, Zechuan Li, Dong Chen, Mingliang Xu

专题命中 Gaussian Splatting :3DGS(summary_cn,abstract);Gaussian Splatting(title,abstract);3D reconstruction(abstract);分类 cs.CV

AI总结 本文提出一种基于2D高斯溅射的高效单对象3D重建方法,通过整合前景-背景概率提示和动态剪枝低概率高斯,提升内存和计算效率,实验表明其在遮罩误差下具有强自修正能力,重建质量接近标准3DGS方法,但高斯数量仅为1/10。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.23221 2026-07-01 cs.CV 版本更新 90%

Robust 3DGS-based SLAM via Adaptive Kernel Smoothing

基于自适应核平滑的鲁棒3DGS SLAM

Shouhe Zhang, Dayong Ren, Wen Jie Li, Piaopiao Yu, Sensen Song, Kaikai Shao, Yurong Qian

机构 * Xinjiang University(新疆大学) Nanjing University(南京大学) Southwest University of Political Science and Law(西南政治科学法学院) Nanjing University of Aeronautics and Astronautics(南京航空航天大学) Yantai University(烟台大学)

专题命中 Gaussian Splatting :3DGS(title,title_cn);分类 cs.CV

AI总结 针对3DGS-SLAM中渲染质量主导跟踪精度的传统观念,提出通过平滑核策略增强光栅化过程对参数误差的鲁棒性,从而稳定相机位姿跟踪,并设计了CB-KNN方法自适应调整局部高斯参数,实验证明在保持建图质量的同时显著提升跟踪鲁棒性和精度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.28581 2026-06-30 cs.CV 90%

SatSplat: Geometrically-Accurate Gaussian Splatting for Satellite Imagery

SatSplat: 面向卫星图像的几何精确高斯泼溅

Shuang Song, Jiyong Kim, Rongjun Qin

机构 * The Ohio State University(俄亥俄州立大学)

专题命中 Gaussian Splatting :3DGS(summary_cn,abstract);Gaussian Splatting(title,abstract);3D reconstruction(abstract);分类 cs.CV

AI总结 提出SatSplat,首个将2D高斯泼溅(2DGS)适配到卫星摄影测量的框架,通过在线相机调整和几何阴影映射,在DFC2019和IARPA2016基准上实现了高几何精度,相比基于3DGS的方法,平均绝对误差降低11.93%,峰值显存减少31%。

Comments Photogrammetric Engineering & Remote Sensing

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.20103 2026-06-19 cs.CV 新提交 90%

Geometry-Preserving in 3D Gaussian Splatting for LiDAR-Camera Extrinsic Calibration

3D高斯溅射中保持几何结构的LiDAR-相机外参标定

Kyoleen Kwak, Daeho Kim, Jeong Woon Lee, Hyoseok Hwang

机构 * Kyung Hee University(庆熙大学)

专题命中 Gaussian Splatting :3DGS(summary_cn,abstract);Gaussian Splatting(title,abstract);novel view synthesis(abstract);分类 cs.CV

AI总结 针对LiDAR-相机标定中跨模态特征稀缺问题,提出通过多视图LiDAR深度监督和阻止光度梯度更新高斯空间参数来保持3DGS代理的度量几何,提升标定精度。

Comments Accepted to ECCV 2026. 15 pages (excluding references), 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.17935 2026-06-17 cs.CV 新提交 90%

MoonSplat: Monocular Online Gaussian Splatting with Sim(3) Global Optimization

MoonSplat: 基于Sim(3)全局优化的单目在线高斯泼溅

Guo Pu, Yixuan Han, Haofeng Li, Yao Zhang, Hui Zhou, Zhouhui Lian

机构 * Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机技术研究所) Beijing Hydrogen Intelligent Tech. Co., Ltd.(北京氢元智能科技有限公司)

专题命中 Gaussian Splatting :3DGS(summary_cn,abstract);Gaussian Splatting(title,abstract);3D reconstruction(abstract);分类 cs.CV

AI总结 提出一种结合Sim(3)全局优化的在线体素化3DGS框架,通过颜色残差学习策略加速收敛,实现鲁棒的相机跟踪和全局闭环,在室内外数据集上达到SOTA性能。

Comments SIGGRAPH 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.02346 2026-06-02 cs.CV 90%

VEDAL: Variational Error-Driven Asynchronous Learning for 3D Gaussian Splatting Pruning

VEDAL: 用于3D高斯泼溅剪枝的变分误差驱动异步学习

Aoduo Li, Jiancheng Li, Huan Ye, Hongjian Xu, Shiting Wu, Xiujun Zhang, Zimeng Li, Xuhang Chen

机构 * Guangdong University of Technology(广东工业大学) Huizhou Boluo Power Supply Bureau, Guangdong Power Grid Co., Ltd.(惠州市博罗供电局,广东电网有限责任公司) Shenzhen Polytechnic University(深圳职业技术大学) School of Computer Science and Engineering, Huizhou University(惠州市大学计算机科学与工程学院)

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);NeRF(abstract,abstract_cn);3DGS(abstract,abstract_cn);novel view synthesis(abstract)

AI总结 提出VEDAL框架,通过变分自由能最小化、预测误差门控机制和变分不确定性头实现3D高斯泼溅的高效剪枝,在5.2倍压缩下仅损失0.31 dB PSNR。

Comments 12 pages, 5 figures. Accepted by CGI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏