3D 视觉

Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics

Junyi Cao, Shanyan Guan, Yanhao Ge, Wei Li, Xiaokang Yang, Chao Ma

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

Comments NeurIPS 2024, the project page: https://xjay18.github.io/projects/neuma.html

DifFRelight: Diffusion-Based Facial Performance Relighting

Mingming He, Pascal Clausen, Ahmet Levent Taşel, Li Ma, Oliver Pilarski, Wenqi Xian, Laszlo Rikker, Xueming Yu, Ryan Burgert, Ning Yu, Paul Debevec

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

Comments 18 pages, SIGGRAPH Asia 2024 Conference Papers (SA Conference Papers '24), December 3--6, 2024, Tokyo, Japan. Project page: https://www.eyelinestudios.com/research/diffrelight.html

3D Gaussian Ray Tracing: Fast Tracing of Particle Scenes

Nicolas Moenne-Loccoz, Ashkan Mirzaei, Or Perel, Riccardo de Lutio, Janick Martinez Esturo, Gavriel State, Sanja Fidler, Nicholas Sharp, Zan Gojcic

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

Comments Project page: https://gaussiantracer.github.io/. Published at SIGGRAPH Asia 2024

TextToon: Real-Time Text Toonify Head Avatar from Single Video

Luchuan Song, Lele Chen, Celong Liu, Pinxin Liu, Chenliang Xu

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

Comments Project Page: https://songluchuan.github.io/TextToon/

V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians

Penghao Wang, Zhirui Zhang, Liao Wang, Kaixin Yao, Siyuan Xie, Jingyi Yu, Minye Wu, Lan Xu

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

Thermal3D-GS: Physics-induced 3D Gaussians for Thermal Infrared Novel-view Synthesis

Qian Chen, Shihao Shu, Xiangzhi Bai

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

Comments 17 pages, 4 figures, 3 tables

Journal ref ECCV2024

GraspSplats: Efficient Manipulation with 3D Feature Splatting

Mazeyu Ji, Ri-Zhao Qiu, Xueyan Zou, Xiaolong Wang

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

Comments Project webpage: https://graspsplats.github.io/

DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object Manipulation

Bardienus P. Duisterhof, Zhao Mandi, Yunchao Yao, Jia-Wei Liu, Jenny Seidenschwarz, Mike Zheng Shou, Deva Ramanan, Shuran Song, Stan Birchfield, Bowen Wen, Jeffrey Ichnowski

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

Registering Neural 4D Gaussians for Endoscopic Surgery

Yiming Huang, Beilei Cui, Ikemura Kei, Jiekai Zhang, Long Bai, Hongliang Ren

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

GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions

Junjie Wang, Jiemin Fang, Xiaopeng Zhang, Lingxi Xie, Qi Tian

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

Comments CVPR 2024, Project page: https://GaussianEditor.github.io

HoloDreamer: Holistic 3D Panoramic World Generation from Text Descriptions

Haiyang Zhou, Xinhua Cheng, Wangbo Yu, Yonghong Tian, Li Yuan

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

Comments Homepage: https://zhouhyocean.github.io/holodreamer

Click-Gaussian: Interactive Segmentation to Any 3D Gaussians

Seokhun Choi, Hyeonseop Song, Jaechul Kim, Taehyeong Kim, Hoseok Do

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

Comments Accepted to ECCV 2024. The first two authors contributed equally to this work

GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality

Taoran Yi, Jiemin Fang, Zanwei Zhou, Junjie Wang, Guanjun Wu, Lingxi Xie, Xiaopeng Zhang, Wenyu Liu, Xinggang Wang, Qi Tian

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

Comments Project page: https://taoranyi.com/gaussiandreamerpro/

Efficient Heatmap-Guided 6-Dof Grasp Detection in Cluttered Scenes

Siang Chen, Wei Tang, Pengwei Xie, Wenming Yang, Guijin Wang

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

Comments Extensive results on GraspNet-1B dataset

3D Gaussian Blendshapes for Head Avatar Animation

Shengjie Ma, Yanlin Weng, Tianjia Shao, Kun Zhou

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

Comments ACM SIGGRAPH Conference Proceedings 2024

Learn2Talk: 3D Talking Face Learns from 2D Talking Face

Yixiang Zhuang, Baoping Cheng, Yao Cheng, Yuntao Jin, Renshuai Liu, Chengyang Li, Xuan Cheng, Jing Liao, Juncong Lin

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

Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis

Zhan Li, Zhang Chen, Zhong Li, Yi Xu

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

Comments Accepted to CVPR 2024. Project page: https://oppo-us-research.github.io/SpacetimeGaussians-website/

Gaussian Frosting: Editable Complex Radiance Fields with Real-Time Rendering

Antoine Guédon, Vincent Lepetit

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

Comments Project Webpage: https://anttwo.github.io/frosting/

VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis

Angtian Wang, Peng Wang, Jian Sun, Adam Kortylewski, Alan Yuille

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

Comments Accepted by ICLR2023

DISTWAR: Fast Differentiable Rendering on Raster-based Rendering Pipelines

Sankeerth Durvasula, Adrian Zhao, Fan Chen, Ruofan Liang, Pawan Kumar Sanjaya, Nandita Vijaykumar

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

Mathematical Supplement for the $\texttt{gsplat}$ Library

Vickie Ye, Angjoo Kanazawa

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

Comments Find the library at: https://docs.gsplat.studio/

Gaussian Process Gradient Maps for Loop-Closure Detection in Unstructured Planetary Environments

Cedric Le Gentil, Mallikarjuna Vayugundla, Riccardo Giubilato, Wolfgang Stürzl, Teresa Vidal-Calleja, Rudolph Triebel

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

Comments This work is accepted for presentation at the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Please find IEEE's copyright statement at the bottom of the first page. Cedric Le Gentil and Mallikarjuna Vayugundla share the first authorship of this paper

Direct Fitting of Gaussian Mixture Models

Leonid Keselman, Martial Hebert

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

Comments Accepted to the Conference on Computer and Robot Vision 2019. 8 pages

Robust Rigid Point Registration based on Convolution of Adaptive Gaussian Mixture Models

Can Pu, Nanbo Li, Robert B Fisher

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

Comments 9 pages

4DAnyone: Create Anyone in 4D from a Casual Monocular Video

4DAnyone：从随意的单目视频中创建4D虚拟人物

Yudong Jin, Tao Xie, Qihang Zhang, Zehong Shen, Zhen Xu, Yujun Shen, Hujun Bao, Xiaowei Zhou, Yinghao Xu

机构 * State Key Lab of CAD&CG, Zhejiang University（浙江大学CAD&CG国家重点实验室） ； Robbyant ； Chinese University of Hong Kong（香港中文大学） ； Ant Group（蚂蚁集团） ； Hong Kong University of Science and Technology（香港科技大学） 纠错

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

AI总结 4DAnyone是一种从单目视频重建4D人体的框架，通过RCP和TCR解决多视图一致性问题，在相关数据集上优于现有方法且泛化性好。

Comments Project page: https://4danyone.github.io

Stream4D: 4D-Consistency for Streaming Autoregressive Diffusion Video Models

Stream4D：面向流式自回归扩散视频模型的4D一致性

Yuanhao Ban, Jiaqi Feng, Hengguang Zhou, Xiaohuan Pei, Justin Cui, Cho-Jui Hsieh

机构 * UCLA（加州大学洛杉矶分校） ； Tsinghua University（清华大学） 纠错

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

AI总结 Stream4D用显式建模场景动力学的前馈4D重建奖励替代静态评判器，结合运动先验与感知锚，提升流式自回归扩散视频模型的4D重建质量、运动保留效果及人类对齐偏好。

GaussMemory: Task-Driven 3D Gaussian Scene Memory for Long-Horizon Robotic Manipulation

GaussMemory：面向长时程机器人操作的任务驱动三维高斯场景记忆

Zhiqiang Hu, Shouren Huang, Masatoshi Ishikawa

机构 * Research Institute for Science & Technology, Tokyo University of Science（东京理科大学科学技术研究所） 纠错

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

AI总结 该研究针对现有三维机器人记忆系统被动存储的缺陷，提出任务驱动的主动场景记忆框架GaussMemory，在LIBERO、VLABench基准上超越了MemoryVLA、π₀-FAST等方法。

Comments 8 pages, 10 figures. Accepted to the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026)

Standalone DINOv3 for Training-Free Open-Vocabulary Semantic Segmentation in Remote Sensing

用于遥感领域无需训练的开放词汇语义分割的独立DINOv3模型

Changhao Zhao, Haoxiang Li, Yuke Li, Hai Liu, LingLin Zeng

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

AI总结 针对遥感语义分割标注成本高的问题，提出无需训练的DinoSplat-OV框架，结合DINOv3的文本感知拉普拉斯传播与高斯溅射上采样模块，在多数据集上取得优于现有方法的性能，填补了DINO系列模型在该领域的空白。

CLEAR: Conflict-aware Learning via Evidence-guided Adaptive Routing for Unified Sparse-View 3D Gaussian Super-Resolution

CLEAR：面向统一稀疏视图三维高斯超分辨率的证据引导自适应路由的冲突感知学习

Hantang Li, Qiang Zhu, Xiandong Meng, Debin Zhao, Xiaopeng Fan

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

AI总结 针对稀疏视图三维高斯超分辨率的误差累积问题，提出首个统一单阶段框架CLEAR，通过冲突感知优化、证据引导路由等技术，在4×超分辨率基准上实现了最优渲染质量与几何保真度。

Comments 9 pages, 5 figures

HyperGS: Fast and Generalizable Gaussian Video Representation

HyperGS：快速且通用的高斯视频表示

Fatimah Zohra, Chen Zhao, Shuming Liu, Yahya Al Malallah, Bernard Ghanem

机构 * King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学） ； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）） 纠错

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

AI总结 研究针对高斯视频表示中现有方法依赖单视频优化、编码慢且通用性受限的问题，提出HyperGS方法，通过设计特定Transformer提取令牌和获得高斯表示，结合正则化器解决退化问题，实现快速编码及跨视频通用，提升了PSNR。