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。

2026-05-13 至 2026-05-13 共收录 12 信号源:cs.CV, cs.GR, cs.RO

1. Gaussian Splatting 12 篇

2605.12437 2026-05-13 cs.CV 94%

3D Gaussian Splatting for Efficient Retrospective Dynamic Scene Novel View Synthesis with a Standardized Benchmark

基于3D高斯点划的高效回顾性动态场景新视角合成与标准化基准

Yunxiao Zhang, Suryansh Kumar

机构 * Visual and Spatial AI Lab(视觉与空间人工智能实验室) VCCM Section College of PVFA(VCCM学院光电工程学院) Department of ECEN(电子工程系) Department of CSCE(计算机科学与工程系) Texas A&M University(德克萨斯A&M大学)

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

AI总结 本文提出基于同步多视角动态场景的3D高斯点划方法,无需时间耦合约束即可实现高效回顾性动态场景新视角合成,并构建了标准化的动态多视角数据集框架以支持可重复的NeRF和3DGS研究。

Comments Accepted for publication at CVPR 2026; 4D World Models Workshop. Draft info: 14 pages, 4 figures, 8 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.11266 2026-05-13 cs.CV cs.GR cs.LG 93%

PG-3DGS: Optimizing 3D Gaussian Splatting to Satisfy Physics Objectives

PG-3DGS:优化3D高斯点云以满足物理目标

Zachary Lee, Maxwell Jacobson, Yexiang Xue

机构 * Department of Computer Science, Purdue University(普渡大学计算机科学系)

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

AI总结 PG-3DGS通过结合可微物理模拟与3D高斯表示,生成符合物理功能的3D结构,实现视觉与物理功能的平衡。

Comments Submitted to Artificial Intelligence. 52 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.11489 2026-05-13 cs.GR cs.CV 91%

3DGS$^3$: Joint Super Sampling and Frame Interpolation for Real-Time Large-Scale 3DGS Rendering

3DGS$^3$:联合超采样与帧插值用于实时大规模3DGS渲染

Yibo Zhao, Fan Gao, Youcheng Cai, 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);分类 cs.CV、cs.GR

AI总结 本文提出3DGS$^3$框架,通过联合超采样和帧插值提升实时大规模3DGS渲染的效率与质量,采用可微处理实现高分辨率和高帧率输出。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.14199 2026-05-13 eess.IV cs.CV eess.SP 91%

Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation

可学习的多级离散小波变换用于3D高斯点划频率调制

Hung Nguyen, An Le, Truong Nguyen

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

AI总结 本文提出基于多级DWT的3DGS频率调制框架,通过递归分解低频子带,构建更深层的课程,减少高斯点数量并保持渲染质量。

Comments Accepted to EUSIPCO 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.11432 2026-05-13 eess.SP 88%

XFreq-GS: Cross-Frequency Wireless Radiation Field Reconstruction with 3D Gaussian Splatting

XFreq-GS: 基于3D高斯点云的跨频无线辐射场重建

Sheng Wang, Hengtao He, Chaozheng Wen, Jingwen Tong, Xinyu Li, Xiao Li, Jun Zhang, Shi Jin

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

AI总结 本文提出XFreq-GS框架,通过共享几何和频适应射频属性的3D高斯点云实现跨频无线辐射场重建,并合成功率角谱图,优于现有3DGS方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.11427 2026-05-13 cs.CV 87%

PD-4DGS:Progressive Decomposition of 4D Gaussian Splatting for Bandwidth-Adaptive Dynamic Scene Streaming

PD-4DGS:4D高斯散射的渐进分解用于带宽自适应动态场景流媒体

Jiachen Li, Guangzhi Han, Jin Wan, Delong Han, Yuan Gao, Min Li, Mingle Zhou, Gang Li

机构 * Qilu University of Technology(青岛理工大学)

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

AI总结 PD-4DGS通过渐进压缩和按需传输实现4D高斯散射的高效流媒体,减少带宽消耗并降低延迟,提升动态场景渲染性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12144 2026-05-13 cs.CV 86%

PoseCompass: Intelligent Synthetic Pose Selection for Visual Localization

PoseCompass: 用于视觉定位的智能合成姿态选择

Yanan Zhou, Zhaoyan Qian, Yanli Li, Nan Yang, Zhongliang Guo, Dong Yuan

机构 * The University of Sydney(悉尼大学) University of St Andrews(圣安德鲁大学)

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

AI总结 PoseCompass通过智能姿态选择提升基于3DGS的APR性能,减少适应时间并降低姿态误差,优于随机基线。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12399 2026-05-13 cs.CV 84%

GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction

GeoQuery: 用于稀疏视角重建的几何-查询扩散

Xiao Cao, Yuze Li, Youmin Zhang, Jiayu Song, Cheng Yan, Wen Li, Lixin Duan

机构 * University of Electronic Science Tianjin University Tianjin China Tianjin University

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

AI总结 本文提出GeoQuery,通过几何引导的扩散框架,在稀疏视角重建中有效减少渲染伪影。

Comments Accept to SIGGRAPH 2026 Conference Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.11424 2026-05-13 cs.CV 79%

VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors

VidSplat:基于几何引导视频扩散先验的高斯点云重建

Jimin Tang, Wenyuan Zhang, Junsheng Zhou, Zian Huang, Kanle Shi, Shenkun Xu, Yu-Shen Liu, Zhizhong Han

机构 * School of Software, Tsinghua University(清华大学软件学院) Department of Computer Science, Wayne State University(韦恩州立大学计算机科学系)

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

AI总结 VidSplat通过几何引导的视频扩散先验,解决稀疏视图下3D场景重建问题,提出免训练生成框架,迭代合成新视角以恢复完整3D场景。

Comments Accepted by SIGGRAPH Conference 2026. Project Page: https://tangjm24.github.io/VidSplat

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.11144 2026-05-13 cs.RO 79%

Forecast-aware Gaussian Splatting for Predictive 3D Representation in Language-Guided Pick-and-Place Manipulation

面向预测的高斯点散布用于语言引导的抓取与放置操作中的预测3D表示

Kaixin Jia, Jiacheng Xu

机构 * KTH Royal Institute of Technology(皇家理工学院)

专题命中 Gaussian Splatting :Gaussian Splatting(title,abstract);分类 cs.RO

AI总结 本文提出Forecast-GS框架,通过预测3D状态提升语言引导的机器人操作性能,实验显示其在抓取与放置任务中优于基线方法,表明明确预测任务完成状态有助于更可靠的行动评估。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.11594 2026-05-13 cs.CV 77%

PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations

PointForward:通过点对齐表示实现馈送驾驶重建

Cheng Chi, Xianqi Wang, Hongcheng Luo, Mingfei Tu, Gangwei Xu, Zehan Zhang, Bing Wang, Guang Chen, Hangjun Ye, Sida Peng, Xin Yang, Haiyang Sun

机构 * Xiaomi EV(小米电动车) Huazhong University of Science and Technology(华中科技大学) Zhejiang University(浙江大学)

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

AI总结 PointForward通过点对齐表示实现驾驶场景重建,采用空间时间融合提升多视角一致性,引入场景图处理动态实例,实现高精度驾驶场景重建。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.12494 2026-05-13 cs.CV 70%

Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction

重新审视光度歧义以实现高精度高斯-散射表面重建

Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xiaohan Yu, Lin Gu, Gim Hee Lee

机构 * School of Computer Science Engineering, State Key Laboratory of Complex Critical \& Software Environment, Jiangxi Research Institute, Beihang University State Key Laboratory of Virtual Reality Technology Macquarie University Tohoku University School of Computing, National University of Singapore

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

AI总结 本文提出AmbiSuR框架,通过高斯散射内在解决方案解决光度歧义问题,提升3D表面重建性能,实验显示在多种挑战场景中表现优异。

Comments Accepted at ICML 2026. Project page: https://fictionarry.github.io/AmbiSuR-Proj/

详情

展开后加载摘要…

URL PDF HTML 收藏