3D 视觉

Tele-Aloha: A Low-budget and High-authenticity Telepresence System Using Sparse RGB Cameras

Hanzhang Tu, Ruizhi Shao, Xue Dong, Shunyuan Zheng, Hao Zhang, Lili Chen, Meili Wang, Wenyu Li, Siyan Ma, Shengping Zhang, Boyao Zhou, Yebin Liu

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

Comments Paper accepted by SIGGRAPH 2024. Project page: http://118.178.32.38/c/Tele-Aloha/

Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping

Tianhao Wu, Jing Yang, Zhilin Guo, Jingyi Wan, Fangcheng Zhong, Cengiz Oztireli

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

Comments Project Page: https://gaussian-head-shoulders.netlify.app/

MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections

Jiayue Liu, Xiao Tang, Freeman Cheng, Roy Yang, Zhihao Li, Jianzhuang Liu, Yi Huang, Jiaqi Lin, Shiyong Liu, Xiaofei Wu, Songcen Xu, Chun Yuan

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

GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation

Quankai Gao, Qiangeng Xu, Zhe Cao, Ben Mildenhall, Wenchao Ma, Le Chen, Danhang Tang, Ulrich Neumann

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

OneTo3D: One Image to Re-editable Dynamic 3D Model and Video Generation

Jinwei Lin

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

Comments 24 pages, 13 figures, 2 tables

DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalization

Jiahe Li, Jiawei Zhang, Xiao Bai, Jin Zheng, Xin Ning, Jun Zhou, Lin Gu

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

Comments Accepted at CVPR 2024. Project page: https://fictionarry.github.io/DNGaussian/

Rig3DGS: Creating Controllable Portraits from Casual Monocular Videos

Alfredo Rivero, ShahRukh Athar, Zhixin Shu, Dimitris Samaras

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

Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities

Xu Yan, Haiming Zhang, Yingjie Cai, Jingming Guo, Weichao Qiu, Bin Gao, Kaiqiang Zhou, Yue Zhao, Huan Jin, Jiantao Gao, Zhen Li, Lihui Jiang, Wei Zhang, Hongbo Zhang, Dengxin Dai, Bingbing Liu

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

Comments Github Repo: https://github.com/zhanghm1995/Forge_VFM4AD

Human101: Training 100+FPS Human Gaussians in 100s from 1 View

Mingwei Li, Jiachen Tao, Zongxin Yang, Yi Yang

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

Comments Website: https://github.com/longxiang-ai/Human101

MonoGaussianAvatar: Monocular Gaussian Point-based Head Avatar

Yufan Chen, Lizhen Wang, Qijing Li, Hongjiang Xiao, Shengping Zhang, Hongxun Yao, Yebin Liu

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

Comments The link to our projectpage is https://yufan1012.github.io/MonoGaussianAvatar

DynFOA: Generating First-Order Ambisonics with Conditional Diffusion for Dynamic and Acoustically Complex 360-Degree Videos

DynFOA: 基于条件扩散的动态和声学复杂的360度视频生成一阶混响

Ziyu Luo, Lin Chen, Qiang Qu, Xiaoming Chen, Yiran Shen

机构 * School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing, China（计算机与人工智能学院，北京技术与商业大学） ； School of Computer Science, The University of Sydney, Sydney, NSW, Australia（计算机科学学院，悉尼大学） ； School of Software, Shandong University, Jinan, China（软件学院，山东大学） 纠错

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

AI总结 DynFOA通过动态声学感知和条件扩散生成高质量的360度视频一阶混响，提升沉浸式音频体验。

Comments Revised version with updated content.This submission is the intended replacement of arXiv:2602.06846

Learning 3D-Gaussian Simulators from RGB Videos

从RGB视频学习3D高斯模拟器

Mikel Zhobro, Andreas René Geist, Georg Martius

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

AI总结 提出3DGSim，一种从多视角RGB视频直接学习物理交互的3D模拟器，统一了3D场景重建、粒子动力学预测和视频合成，能泛化到未见过的多体交互和新场景编辑。

PropSplat: Map-Free RF Field Reconstruction via 3D Gaussian Propagation Splatting

PropSplat: 通过3D高斯传播散射实现无地图的射频场重建

William Bjorndahl, Maninder Pal Singh, Farhad Nouri, Joseph Camp

机构 * Department of Electrical and Computer Engineering, Southern Methodist University, Dallas, TX, USA（电气与计算机工程系，南方 Methodist 大学，德克萨斯州达拉斯市） ； Department of Engineering Technology, University of Houston, Houston, TX, USA（工程技术系，德克萨斯大学休斯敦分校） 纠错

专题命中 Gaussian Splatting ：NeRF(abstract,abstract_cn)

AI总结 PropSplat利用3D各向异性高斯体重建射频场，无需地理数据或外部信息，通过端到端优化实现精准传播建模，优于现有方法。

Comments Accepted for presentation at IEEE DySPAN 2026

Point Group Symmetry of Polyhedral Diagrams in Graphic Statics

多面体图在图形静力学中的点群对称性

Yefan Zhi, Yao Lu, Masoud Akbarzadeh

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

AI总结 本文研究多面体图在三维图形静力学中的对称性，通过点群约束保持对称性，提出基于边长的对称性约束方法，提升设计效率与实用性。

DynFOA: Generating First-Order Ambisonics with Conditional Diffusion for Dynamic and Acoustically Complex 360-Degree Videos

DynFOA: 利用条件扩散生成动态和声学复杂的360度视频的首阶混响

Ziyu Luo, Lin Chen, Qiang Qu, Xiaoming Chen, Yiran Shen

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

AI总结 本文提出DynFOA，通过整合动态场景重建与条件扩散模型，从360度视频生成首阶混响，解决复杂场景中声学效果建模问题，实验表明其在空间准确性、声学保真度等方面优于现有方法。

Comments Accidental duplicate submission. This paper was intended to be a replacement (v2) for arXiv:2602.06846

Three-Dimensional MRI Reconstruction with Gaussian Representations: Tackling the Undersampling Problem

三维MRI重建与高斯表示：解决欠采样问题

Tengya Peng, Ruyi Zha, Zhen Li, Xiaofeng Liu, Qing Zou

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

AI总结 本文提出3D高斯MRI框架，利用高斯分布重建等效分辨率的3D MRI，无需大量数据集，有效提升重建质量。

Interactive Augmented Reality-enabled Outdoor Scene Visualization For Enhanced Real-time Disaster Response

交互式增强现实赋能的户外场景可视化以提升实时灾害响应

Dimitrios Apostolakis, Georgios Angelidis, Vasileios Argyriou, Panagiotis Sarigiannidis, Georgios Th. Papadopoulos

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

AI总结 本文提出了一种基于3DGS的交互式AR界面，用于提升实时灾害响应中的场景可视化与决策效率。

Comments 6 pages, 2 figures

EAST: Environment-Aware Stylized Transition Along the Reality-Virtuality Continuum

EAST：环境感知的风格化过渡沿现实-虚拟连续体

Xiaohan Zhang, Kan Liu, Yangle Liu, Fengze Li, Jieming Ma, Yue Li

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

AI总结 EAST通过风格化过渡技术，在现实-虚拟连续体中实现无缝的审美一致性，提升VR体验中的沉浸感和情感连续性。

One Walk is All You Need: Data-Efficient 3D RF Scene Reconstruction with Human Movements

一步即可：利用人体运动进行数据高效的3D射线场场景重建

Yiheng Bian, Zechen Li, Lanqing Yang, Hao Pan, Yezhou Wang, Longyuan Ge, Jeffery Wu, Ruiheng Liu, Yongjian Fu, Yichao chen, Guangtao xue

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

AI总结 本文提出利用人体行走数据高效重建被遮挡3D场景的射线场，通过无结构运动信号提升重建精度，实现数据采集瓶颈的突破。

EGSTalker: Real-Time Audio-Driven Talking Head Generation with Efficient Gaussian Deformation

Tianheng Zhu, Yinfeng Yu, Liejun Wang, Fuchun Sun, Wendong Zheng

机构 * Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, School of Computer Science and Technology, Xinjiang University（新疆多模态智能处理与信息安全部门工程技术研究中心，计算机科学与技术学院，新疆大学） ； Department of Computer Science and Technology, Tsinghua University（计算机科学与技术系，清华大学） ； School of Electrical Engineering and Automation, Tianjin University of Technology（电气工程与自动化学院，天津理工大学） 纠错

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

Comments Main paper (6 pages). Accepted for publication by IEEE International Conference on Systems, Man, and Cybernetics 2025

Distance and Collision Probability Estimation from Gaussian Surface Models

Kshitij Goel, Wennie Tabib

机构 * The Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所） 纠错

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

Comments Accepted at IROS 2025

Lumina: Real-Time Mobile Neural Rendering by Exploiting Computational Redundancy

Yu Feng, Weikai Lin, Yuge Cheng, Zihan Liu, Jingwen Leng, Minyi Guo, Chen Chen, Shixuan Sun, Yuhao Zhu

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

Scan, Materialize, Simulate: A Generalizable Framework for Physically Grounded Robot Planning

Amine Elhafsi, Daniel Morton, Marco Pavone

机构 * Stanford University（斯坦福大学） ； NVIDIA Research（NVIDIA研究） 纠错

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

Visualizing the Invisible: A Generative AR System for Intuitive Multi-Modal Sensor Data Presentation

Yunqi Guo, Kaiyuan Hou, Heming Fu, Hongkai Chen, Zhenyu Yan, Guoliang Xing, Xiaofan Jiang

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

AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis

Swapnil Bhosale, Haosen Yang, Diptesh Kanojia, Jiankang Deng, Xiatian Zhu

机构 * University of Surrey（萨里大学） ； Imperial College London（帝国理工学院） 纠错

专题命中 Gaussian Splatting ：NeRF(abstract)；Gaussian Splatting(abstract)

Comments Accepted to NeurIPS 2024

Infinite Leagues Under the Sea: Photorealistic 3D Underwater Terrain Generation by Latent Fractal Diffusion Models

Tianyi Zhang, Weiming Zhi, Joshua Mangelson, Matthew Johnson-Roberson

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Brigham Young University（杨百翰大学） 纠错

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

Comments 10 pages

TSOG: A Format For Temporally And Spatially Ordered Gaussians

TSOG：时空有序高斯格式

Shady Gmira, Evangelos Alexiou, Emmanouil Potetsianakis, Emmanuel Thomas

机构 * Xiaomi Technology Netherlands B.V（小米科技荷兰有限公司） 纠错

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

AI总结 该研究提出TSOG格式，扩展SOG框架至时间域以高效表示4DGS内容，经评估其文件大小缩减超90%且质量下降极小，可实现动态4D内容的高效存储与传输。

Comments 2026 IEEE International Conference on Image Processing (ICIP). IEEE, 2026

ECoNGS: Efficient Compressive Neural Gaussian Splats for Volume Visualization

ECoNGS：用于体数据可视化的高效压缩神经高斯点云

Kaiyuan Tang, Chaoli Wang

机构 * University of Notre Dame（圣母大学） 纠错

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

AI总结 研究针对大型数据集体数据可视化，提出ECoNGS框架，用轻量级神经网络从显式锚点预测隐式高斯点云，结合联合学习策略、神经熵模型压缩及特定初始化策略，相比iVR-GS在多方面性能更优。

Comments To be published in Proceedings of IEEE VIS 2026, IEEE Transactions on Visualization and Computer Graphics

TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations

TerraTransfer: 无需专家示范的端到端驾驶策略学习

Zikang Xiong, Weixin Li, Zhouchonghao Wu, Akshay Rangesh, Saarth Bonde, Grantland Hall, Chen Tang, Yihan Hu, Wei Zhan

机构 * Applied Intuition ； UCLA（加州大学洛杉矶分校） ； UC Berkeley（加州大学伯克利分校） 纠错

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

AI总结 提出一种无需专家示范的端到端驾驶方法，通过向量化模拟器中的自博弈预训练策略，再与预训练视觉骨干对齐，降低了数据成本并达到或超越现有方法。

Learning Physics-Guided Residual Dynamics for Deformable Object Simulation

学习用于可变形物体模拟的物理引导残差动力学

Shivansh Patel, Kaifeng Zhang, Sanjay Pokkali, Svetlana Lazebnik, Yunzhu Li

机构 * UIUC（伊利诺伊大学厄巴纳 - 香槟分校） ； Columbia University（哥伦比亚大学） 纠错

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

AI总结 研究针对可变形物体模拟中动力学预测难的问题，提出物理引导残差动力学（PGRD）框架，结合物理与学习方法优势，采用特定架构和公式，在多物体模拟上结果更准，还展示了其在操作规划和交互式模拟中的应用效用。

Comments Website: https://pgrd-robot.github.io/