3D 视觉

Fast Learning of Non-Cooperative Spacecraft 3D Models through Primitive Initialization

通过原始初始化快速学习非合作航天器3D模型

Pol Francesch Huc, Emily Bates, Simone D'Amico

机构 * Stanford University（斯坦福大学） 纠错

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

AI总结 本文提出基于CNN的3DGS原始初始化方法，通过单目图像快速学习航天器3D模型，降低训练成本并适应噪声姿态估计。

Journal ref 2025 AAS/AIAA Astrodynamics Specialist Conference, Boston, Massachusetts

Time-Archival Camera Virtualization for Sports and Visual Performances

体育与视觉表演中的时间存档摄像机虚拟化

Yunxiao Zhang, William Stone, Suryansh Kumar

机构 * Spatial AI Lab, Visual Computing \& Computational Media (VCCM) Section ； organization= College of Performance, Visualization ； organization= Department of Electrical ； organization= Department of Computer Science ； organization= Texas A\&M University , city= College Station , state= Texas , country= USA 纠错

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

AI总结 本文提出了一种基于神经体积渲染的摄像机虚拟化方法，通过时间存档能力提升动态场景的逼真渲染和回放效果。

Comments Project Page: https://yunxiaozhangjack.com/tacv/; Under minor revision in Journal of Computer Vision and Image Understanding (CVIU); Special Issue: Computer Vision for Sports and Winter Sports. Outcome of a master and bachelor student project completed in Visual and Spatial AI Lab at TAMU

What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models

机器人中最佳的3D场景表示是什么？从几何到基础模型

Tianchen Deng, Yue Pan, Shenghai Yuan, Dong Li, Chen Wang, Mingrui Li, Long Chen, Lihua Xie, Danwei Wang, Jingchuan Wang, Javier Civera, Hesheng Wang, Weidong Chen

专题命中 Gaussian Splatting ：NeRF(abstract)；Gaussian Splatting(abstract)；3DGS(abstract)；point cloud(abstract)

AI总结 本文探讨了机器人中最佳的3D场景表示方法，对比了传统和神经表示的优劣，并展望了基础模型在机器人应用中的潜力。

DeclutterNeRF: Generative-Free 3D Scene Recovery for Occlusion Removal

Wanzhou Liu, Zhexiao Xiong, Xinyu Li, Nathan Jacobs

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

Comments Accepted by CVPR 2025 4th CV4Metaverse Workshop. 15 pages, 10 figures. Code and data at: https://github.com/wanzhouliu/declutter-nerf

Point-Cloud-Assistant Localized Statistical Channel Prediction by Tangent Gaussian Splatting

点云辅助的切线高斯溅射局部统计信道预测

Ye Xue, Yiheng Wang, Xinhua Shao, Qi Yan, Shutao Zhang, Tsung-Hui Chang

机构 * China Telecom（中国电信） 纠错

专题命中 Gaussian Splatting ：Gaussian Splatting(title,abstract)；point cloud(abstract)

AI总结 提出点云辅助切线高斯溅射（PC-TGS）框架，通过融合稀疏无线电测量与密集LiDAR几何数据，将角功率谱外推到未测量网格，实现大规模无线数字孪生中的高效信道预测。

Journal ref IEEE Trans. Wireless Commun. 25, 17816-17830 (2026)

Super-Gaussian: Interactive Scene Editing for 3D Gaussian Splatting and NLI-Based Volume Visualization in Virtual Reality

超高斯：虚拟现实中面向三维高斯溅射与基于自然语言交互的体可视化的交互式场景编辑

Suemin Jeon, Kaiyuan Tang, Chaoli Wang, Won-Ki Jeong

专题命中 Gaussian Splatting ：Gaussian Splatting(title,abstract)

AI总结 本研究针对VR中体可视化的渲染成本与交互问题，提出Super-Gaussian框架，结合三维高斯溅射、特征感知聚类、分层选择-细化工作流与NLI，实现高效直观的体数据交互编辑与分析

Comments IEEE VIS 2026 accepted

StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction

StructureGS：面向关节物体重建的结构感知高斯溅射

Gahye Lee, Gyoonseo Kim, Wonjong Jang, Jooeun Son, Seungyong Lee

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

AI总结 该研究针对关节物体重建中参数纠缠导致的部件分解缺陷，提出StructureGS框架，结合结构感知引导的3D高斯溅射，通过定向包围盒约束实现更优重建性能。

Comments accepted at ECCV 2026

FillGauss: Fine-Grained Filling-Aware Impact Sound Generation for 3D Gaussian Splatting

FillGauss：用于3D高斯点云的细粒度填充感知撞击声生成

Chen Yang, Ganye Wen, Bin Huang, Jiayi Lyu, Zehai Niu, Linlin Shen, Jinbao Wang

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

AI总结 研究针对多模态AI中从视觉合成撞击声的挑战，提出细粒度填充感知撞击声生成任务。基于FillImpact数据集，构建FillGauss框架，融合多种要素实现位置、撞击物及填充感知音频生成，达物理基础跨模态音频生成新水平。

SyncSpace: Layout-Conditioned 3D Gaussian Splatting for Space Reskinning in Mixed Reality

SyncSpace：用于混合现实中空间重塑的布局条件3D高斯溅射

Qinchuan Zhang, Weibo Xu, Yunge Wen

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

AI总结 SyncSpace系统通过深度感应提取3D边界框，经生成世界模型生成高斯溅射场景，再用粗到精算法与物理空间对齐，实现空间重塑，可展示手部跟踪吞噬交互及同一空间重塑为多风格世界。

Comments 2 pages, 2 figures

LiftNav: Path Planning via Semantic Lifting in TSDF-Guided Gaussian Splatting

LiftNav: TSDF引导的高斯泼溅中的语义提升路径规划

Hannah Schieber, Dominik Frischmann, Victor Schaack, Angela P. Schoellig, Daniel Roth

机构 * Technical University of Munich（慕尼黑技术大学） ； Human-Centered Computing and Extended Reality Lab（以人为本计算与扩展现实实验室） ； TUM University Hospital（慕尼黑大学医院） ； Clinic for Orthopedics and Sports Orthopedics（骨科与运动医学诊所） ； Munich Institute of Robotics and Machine Intelligence (MIRMI)（慕尼黑机器人与机器智能研究所） ； Learning Systems and Robotics Lab（学习系统与机器人实验室） 纠错

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

AI总结 提出LiftNav混合导航框架，结合TSDF+GS双地图、YOLO检测、TSDF三维提升和B样条轨迹优化，实现无需密集三维嵌入的灵活语义导航，并通过铰链损失碰撞惩罚提升轨迹平滑性和安全性，在Replica数据集仿真中实现100%可行性和更短轨迹。

AudioGS: Spectrogram-Based Audio Gaussian Splatting for Sound Field Reconstruction

AudioGS：基于频谱的音频高斯点云用于声音场重建

Chunhao Bi, Houqiang Zhong, Zhixin Xu, Li Song, Zhengxue Cheng

机构 * School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院） ； Institute of Cultural and Creative Industry, Shanghai Jiao Tong University（上海交通大学文创学院） 纠错

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

AI总结 AudioGS通过频谱构建音频高斯点云，无需视觉先验，有效重建空间音频，实验显示其在MAG和DPAM指标上优于现有方法。

GEAR: GEometry-motion Alternating Refinement for Articulated Object Modeling with Gaussian Splatting

GEAR: 基于高斯点划法的几何-运动交替优化用于关节物体建模

Jialin Li, Bin Fu, Ruiping Wang, Xilin Chen

机构 * Key Laboratory of AI Safety of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS（中国科学院人工智能安全重点实验室，中国科学院计算技术研究所） ； University of Chinese Academy of Sciences（中国科学院大学） 纠错

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

AI总结 GEAR通过交替优化几何与运动，提升关节物体重建的精度和泛化能力，尤其在复杂多关节物体上表现优异。

Comments Accepted to CVPRF2026

SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes

SpectralSplat：面向驾驶场景的外观-解耦前馈高斯点云法

Quentin Herau, Tianshuo Xu, Depu Meng, Jiezhi Yang, Chensheng Peng, Spencer Sherk, Yihan Hu, Wei Zhan

机构 * Applied Intuition ； The Hong Kong University of Science and Technology（香港科技大学） ； University of California, Berkeley（加州大学伯克利分校） 纠错

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

AI总结 SpectralSplat通过前馈高斯点云法解耦场景几何与外观属性，提升驾驶场景的重建质量和可控外观迁移能力。

Comments Under review

Wideband RF Radiance Field Modeling Using Frequency-embedded 3D Gaussian Splatting

基于嵌入频率的3D高斯点云的宽频带RF辐射场建模

Zechen Li, Lanqing Yang, Yiheng Bian, Hao Pan, Yongjian Fu, Yezhou Wang, Zhuxi Chen, Yi-Chao Chen, Guangtao Xue

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

AI总结 本文提出一种新型3DGS算法，用于统一宽频带RF辐射场建模，通过嵌入频率的电磁特征网络，在不同频率下高效重建辐射场。

Comments This paper is withdrawn because the technical approach has been significantly updated. The methods and results in this version are no longer representative of the latest research progress

FreeArtGS: Articulated Gaussian Splatting Under Free-moving Scenario

FreeArtGS: 自由移动场景下的关节高斯溅射重建

Hang Dai, Hongwei Fan, Han Zhang, Duojin Wu, Jiyao Zhang, Hao Dong

机构 * CFCS, School of Computer Science, Peking University（计算机科学系，北京大学CFCS） ； College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） ； PrimeBot 纠错

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

AI总结 FreeArtGS通过自由移动部分分割、关节估计和端到端优化，实现高可扩展性的自由移动关节物体重建，实验表明其在真实资产生成中具有实用性。

Comments Accepted to CVPR 2026

FLICKER: A Fine-Grained Contribution-Aware Accelerator for Real-Time 3D Gaussian Splatting

FLICKER: 一种细粒度贡献感知的实时3D高斯散射加速器

Wenhui Ou, Zhuoyu Wu, Yipu Zhang, Dongjun Wu, Freddy Ziyang Hong, Chik Patrick Yue

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

AI总结 FLICKER通过细粒度贡献感知技术，实现实时3D高斯散射加速，提升速度和能效1.5至26.7倍。

Comments Accepted at DATE 2026 (Design, Automation and Test in Europe Conference)

Position: 3D Gaussian Splatting Watermarking Should Be Scenario-Driven and Threat-Model Explicit

位置：3D高斯散射水印应基于场景驱动和威胁模型明确

Yangfan Deng, Anirudh Nakra, Min Wu

机构 * University of Maryland, College Park, MD, United States（马里兰大学学院公园分校） 纠错

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

AI总结 本文主张3D资产水印技术应基于场景驱动和威胁模型明确，以提升知识产权保护效果。

Nebula: Enable City-Scale 3D Gaussian Splatting in Virtual Reality via Collaborative Rendering and Accelerated Stereo Rasterization

Nebula: 通过协作渲染和加速立体光栅化实现城市级3D高斯散射

He Zhu, Zheng Liu, Xingyang Li, Anbang Wu, Jieru Zhao, Fangxin Liu, Yiming Gan, Jingwen Leng, Yu Feng

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

AI总结 Nebula通过协作渲染和加速立体光栅化，实现城市级3D高斯散射的高效渲染，显著降低带宽需求并提升VR体验。

Voxel-GS: Quantized Scaffold Gaussian Splatting Compression with Run-Length Coding

体素-GS：基于运行长度编码的量化框架高斯点云压缩

Chunyang Fu, Xiangrui Liu, Shiqi Wang, Zhu Li

专题命中 Gaussian Splatting ：Gaussian Splatting(title,abstract)；point cloud(abstract)

AI总结 Voxel-GS通过运行长度编码和轻量速率代理实现高斯点云的高效压缩，提升编码速度与压缩比。

Comments Accepted by DCC 2026

Splatonic: Architecture Support for 3D Gaussian Splatting SLAM via Sparse Processing

Splatonic：通过稀疏处理支持3D高斯散射SLAM的架构

Xiaotong Huang, He Zhu, Tianrui Ma, Yuxiang Xiong, Fangxin Liu, Zhezhi He, Yiming Gan, Zihan Liu, Jingwen Leng, Yu Feng, Minyi Guo

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

AI总结 Splatonic通过稀疏处理和高效架构设计，实现了3DGS-SLAM在移动设备上的高速度和高能效。

RTGS: Real-Time 3D Gaussian Splatting SLAM via Multi-Level Redundancy Reduction

Leshu Li, Jiayin Qin, Jie Peng, Zishen Wan, Huaizhi Qu, Ye Han, Pingqing Zheng, Hongsen Zhang, Yu Cao, Tianlong Chen, Yang Katie Zhao

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

Comments Accepted by MICRO2025

PINGS: Gaussian Splatting Meets Distance Fields within a Point-Based Implicit Neural Map

Yue Pan, Xingguang Zhong, Liren Jin, Louis Wiesmann, Marija Popović, Jens Behley, Cyrill Stachniss

机构 * Center for Robotics, University of Bonn（博恩大学机器人中心） ； MAVLab, TU Delft（代尔夫特理工大学MAVLab） ； Lamarr Institute for Machine Learning and Artificial Intelligence（德国拉马尔人工智能与机器学习研究所） 纠错

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

Comments 15 pages, 8 figures, presented at RSS 2025

Touch-Augmented Gaussian Splatting for Enhanced 3D Scene Reconstruction

Yuchen Gao, Xiao Xu, Eckehard Steinbach, Daniel E. Lucani, Qi Zhang

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

No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Rendering

Linye Wei, Jiajun Tang, Fan Fei, Boxin Shi, Runsheng Wang, Meng Li

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

Comments Accepted by International Conference on Computer-Aided Design (ICCAD) 2025

3DGauCIM: Accelerating Static/Dynamic 3D Gaussian Splatting via Digital CIM for High Frame Rate Real-Time Edge Rendering

Wei-Hsing Huang, Cheng-Jhih Shih, Jian-Wei Su, Samuel Wade Wang, Vaidehi Garg, Yuyao Kong, Jen-Chun Tien, Nealson Li, Arijit Raychowdhury, Meng-Fan Chang, Yingyan, Lin, Shimeng Yu

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

GCC: A 3DGS Inference Architecture with Gaussian-Wise and Cross-Stage Conditional Processing

Minnan Pei, Gang Li, Junwen Si, Zeyu Zhu, Zitao Mo, Peisong Wang, Zhuoran Song, Xiaoyao Liang, Jian Cheng

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

Comments Accepted to MICRO 2025

Digital-twin imaging based on descattering Gaussian splatting

Suguru Shimomura, Kazuki Yamanouchi, Jun Tanida

专题命中 Gaussian Splatting ：Gaussian Splatting(title,abstract)；point cloud(abstract)

R3GS: Gaussian Splatting for Robust Reconstruction and Relocalization in Unconstrained Image Collections

Xu yan, Zhaohui Wang, Rong Wei, Jingbo Yu, Dong Li, Xiangde Liu

机构 * Beijing Digital Native Digital City Research Center（北京数字原生数字城市研究中心） 纠错

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

Comments 7 pages, 4 figures

Journal ref IEEE International Conference on Robotics and Automation (ICRA),2025

4DGS-CC: A Contextual Coding Framework for 4D Gaussian Splatting Data Compression

Zicong Chen, Zhenghao Chen, Wei Jiang, Wei Wang, Lei Liu, Dong Xu

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

AvatarPerfect: User-Assisted 3D Gaussian Splatting Avatar Refinement with Automatic Pose Suggestion

Jotaro Sakamiya, I-Chao Shen, Jinsong Zhang, Mustafa Doga Dogan, Takeo Igarashi

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

Comments 13 pages