3D 视觉

PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting

Cheng Zhang, Haofei Xu, Qianyi Wu, Camilo Cruz Gambardella, Dinh Phung, Jianfei Cai

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

Comments Camera Ready of CVPR2025. Project Page: https://chengzhag.github.io/publication/pansplat/ Code: https://github.com/chengzhag/PanSplat

Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting

Jinbo Yan, Rui Peng, Zhiyan Wang, Luyang Tang, Jiayu Yang, Jie Liang, Jiahao Wu, Ronggang Wang

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

4D Gaussian Splatting SLAM

Yanyan Li, Youxu Fang, Zunjie Zhu, Kunyi Li, Yong Ding, Federico Tombari

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

Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting

Runsong Zhu, Shi Qiu, Zhengzhe Liu, Ka-Hei Hui, Qianyi Wu, Pheng-Ann Heng, Chi-Wing Fu

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

Comments CVPR 2025. The code is publicly available at this https URL (https://github.com/Runsong123/Unified-Lift)

Deblur Gaussian Splatting SLAM

Francesco Girlanda, Denys Rozumnyi, Marc Pollefeys, Martin R. Oswald

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

VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Frames

Zhiqi Li, Chengrui Dong, Yiming Chen, Zhangchi Huang, Peidong Liu

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

GSVC: Efficient Video Representation and Compression Through 2D Gaussian Splatting

Longan Wang, Yuang Shi, Wei Tsang Ooi

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

FlameGS: Reconstruct flame light field via Gaussian Splatting

Yunhao Shui, Fuhao Zhang, Can Gao, Hao Xue, Zhiyin Ma, Gang Xun, Xuesong Li

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

ChatSplat: 3D Conversational Gaussian Splatting

Hanlin Chen, Fangyin Wei, Gim Hee Lee

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

Topology-aware Human Avatars with Semantically-guided Gaussian Splatting

Haoyu Zhao, Chen Yang, Hao Wang, Xingyue Zhao, Wei Shen

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

MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

Yuedong Chen, Haofei Xu, Chuanxia Zheng, Bohan Zhuang, Marc Pollefeys, Andreas Geiger, Tat-Jen Cham, Jianfei Cai

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

Comments ECCV2024, Project page: https://donydchen.github.io/mvsplat, Code: https://github.com/donydchen/mvsplat

SplatLoc: 3D Gaussian Splatting-based Visual Localization for Augmented Reality

Hongjia Zhai, Xiyu Zhang, Boming Zhao, Hai Li, Yijia He, Zhaopeng Cui, Hujun Bao, Guofeng Zhang

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

TrAME: Trajectory-Anchored Multi-View Editing for Text-Guided 3D Gaussian Splatting Manipulation

Chaofan Luo, Donglin Di, Xun Yang, Yongjia Ma, Zhou Xue, Chen Wei, Yebin Liu

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

A Benchmark for Gaussian Splatting Compression and Quality Assessment Study

Qi Yang, Kaifa Yang, Yuke Xing, Yiling Xu, Zhu Li

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

Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture

Xuanchen Li, Yuhao Cheng, Xingyu Ren, Haozhe Jia, Di Xu, Wenhan Zhu, Yichao Yan

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

VEGS: View Extrapolation of Urban Scenes in 3D Gaussian Splatting using Learned Priors

Sungwon Hwang, Min-Jung Kim, Taewoong Kang, Jayeon Kang, Jaegul Choo

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

Comments The first two authors contributed equally. Project Page: https://vegs3d.github.io/

Physically Embodied Gaussian Splatting: A Realtime Correctable World Model for Robotics

Jad Abou-Chakra, Krishan Rana, Feras Dayoub, Niko Sünderhauf

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

GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting

Chi Yan, Delin Qu, Dan Xu, Bin Zhao, Zhigang Wang, Dong Wang, Xuelong Li

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

Comments Accepted to CVPR 2024(highlight). Project Page: https://gs-slam.github.io/

EndoGSLAM: Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splatting

Kailing Wang, Chen Yang, Yuehao Wang, Sikuang Li, Yan Wang, Qi Dou, Xiaokang Yang, Wei Shen

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

Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

Zeyu Yang, Hongye Yang, Zijie Pan, Li Zhang

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

Comments ICLR 2024

HiFi4G: High-Fidelity Human Performance Rendering via Compact Gaussian Splatting

Yuheng Jiang, Zhehao Shen, Penghao Wang, Zhuo Su, Yu Hong, Yingliang Zhang, Jingyi Yu, Lan Xu

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

OccamView: Object-Conditioned View Selection for Frame-Budgeted Active 3D Gaussian Reconstruction

OccamView：面向帧预算约束下主动式3D高斯重建的物体条件视角选择方法

Hongbo Gao, Wei Zhang, Zeyu Ni, Dihao Zhu, Ruifeng Li, Yunke Wang, Chang Xu

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

AI总结 针对帧预算紧张时现有主动3D高斯重建方法易漏重建物体的问题，提出OccamView框架，通过物体条件视角选择与Geo-Floor机制优化规划，在多数据集上提升了重建表现。

Comments 7 pages, 5 figures. Preprint

Real2Sim2Real for Vision-Language-Action Manipulation: An AMD ROCm-Based Pipeline

用于视觉-语言-动作操纵的Real2Sim2Real：基于AMD ROCm的管道

Qing Yang, Xun Wang, Ziguan Wang, Zhenjiang Li, Hongqiang Wang, Dongdong Weng

机构 * AMD AIG Team（AMD人工智能团队） ； Beijing Institute of Technology（北京理工大学） 纠错

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

AI总结 本文针对视觉-语言-动作操纵提出基于AMD ROCm的Real2Sim2Real技术栈，涵盖多硬件计算，由开放软件栈统一。通过四个演示表明无需CUDA锁定生态系统，展示了在多硬件平台上的相关成果，且管道可在特定硬件和平台上原生运行并重现。

3D-GIMP: When 3D Gaussian Inpainting Meets PatchMatch

3D-GIMP：当3D高斯图像修复与PatchMatch相遇

Xuening Tian, Dieter Schmalstieg, Shohei Mori

机构 * University of Stuttgart（斯图加特大学） 纠错

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

AI总结 针对3D场景编辑中迭代扩散模型的问题，提出3D-GIMP混合范式，通过在关键参考视图进行图像修复并利用3D感知PatchMatch算法传播纹理，优先保证重建一致性，在渲染速度和视图一致性上表现更优。

Comments 15 pages

World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video

世界源于运动：从单目视频生成动态高斯重建

Liyuan Zhu, Shengyu Huang, Amrita Mazumdar, Tianye Li, Zan Gojcic, Gordon Wetzstein, Iro Armeni, Shalini De Mello, Alex Trevithick

机构 * Stanford University（斯坦福大学） ； NVIDIA（英伟达） 纠错

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

AI总结 提出World from Motion方法，利用视频模型从单目视频生成可自由渲染的动态3D高斯表示，通过像素对齐渲染校正伪影并填充缺失区域，实现4D重建新高度。

Comments Project page: https://research.nvidia.com/labs/amri/projects/world-from-motion/

Unpaired RGB-Thermal Gaussian-Splatting Using Visual Geometric Transformers

无配对RGB-热成像高斯泼溅使用视觉几何变换器

Jean Cordonnier, Chenghao Xu, Olga Fink, Malcolm Mielle

机构 * Ecole Polytechnique Federale de Lausanne（瑞士联邦理工学院洛桑分校） ； Schindler EPFL Lab（施耐德EPFL实验室） 纠错

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)；novel view synthesis(abstract)；分类 cs.CV、cs.RO

AI总结 提出一种无配对RGB-热成像新视角合成框架，利用VGGT估计各模态相机位姿并通过Procrustes对齐，结合多模态3D高斯泼溅实现联合重建，在保持RGB保真度的同时实现热成像视图合成。

Comments Accepted at ICRA 2026's Workshop MM-SpatialAI: Multi-Modal Spatial AI for Robust Navigation and Open-World Understanding

Power Foam: Unifying Real-Time Differentiable Ray Tracing and Rasterization

功率泡沫：统一实时可微射线追踪与光栅化

Shrisudhan Govindarajan, Daniel Rebain, Dor Verbin, Kwang Moo Yi, Anish Prabhu, Andrea Tagliasacchi

机构 * Simon Fraser University（西蒙弗雷泽大学） ； University of British Columbia（不列颠哥伦比亚大学） ； Google Deepmind（谷歌DeepMind） ； Google（谷歌） ； University of Toronto（多伦多大学） 纠错

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

AI总结 本文提出一种可微3D表示，结合泡沫射线追踪能力与现代光栅化管线效率，通过可控的功率图实现空间有界原始体，提升实时可微渲染性能。

A Survey of Spatial Memory Representations for Efficient Robot Navigation

一种用于高效机器人导航的空间记忆表示综述

Ma. Madecheen S. Pangaliman, Steven S. Sison, Erwin P. Quilloy, Rowel Atienza

机构 * University of the Philippines Diliman（菲律宾大学杜马扬分校） ； University of Santo Tomas（圣托马斯大学） 纠错

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

AI总结 本文综述了88篇文献，探讨了空间记忆效率问题，提出α指标评估部署可行性，揭示了内存架构对实际部署的影响。

Comments Accepted at the Women in Computer Vision (WiCV) Workshop at CVPR 2026

VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning

VADv2：通过概率规划实现端到端向量自主驾驶

Bo Jiang, Shaoyu Chen, Hao Gao, Bencheng Liao, Qian Zhang, Wenyu Liu, Xinggang Wang

机构 * Huazhong University of Science and Technology（华中科技大学） ； Horizon Robotics 纠错

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

AI总结 本文提出VADv2，一种基于概率规划的端到端自主驾驶模型，通过概率场函数建模动作空间到概率分布的映射，利用大规模驾驶演示提升闭合回路性能，优于现有方法。

Comments Accepted to ICLR 2026. Code is available at https://github.com/hustvl/VAD

Hybrid Latents: Geometry-Appearance-Aware Surfel Splatting

混合隐变量：几何-外观感知的surfel撒点

Neel Kelkar, Simon Niedermayr, Klaus Engel, Rüdiger Westermann

机构 * Technical University of Munich（慕尼黑技术大学） ； Siemens Healthineers（西门子医疗） 纠错

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

AI总结 本文提出一种混合高斯哈希网格辐射表示，通过引入高斯隐变量特征，减少几何与外观的耦合，提升重建精度与渲染效率，实验证明在更少基元下取得更优效果。

Comments 22 pages, 9 figures