3D 视觉 - arXivDaily 专题

1507.05699 2016-05-06 cs.CV 57%

Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians

Peiyun Hu, Deva Ramanan

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

Comments To appear in CVPR 2016

2608.09265 2026-08-11 math.OC math.PR stat.ML 新提交 50%

Entropic Partial Optimal Transport and Partial Gromov--Wasserstein Distance between Gaussian Mixtures

高斯混合模型之间的熵正则化部分最优传输与部分格罗莫夫-瓦瑟斯坦距离

Toshiaki Yachimura, Xiaocheng Zou

专题命中 Gaussian Splatting ：point cloud(abstract)

AI总结本文针对高斯混合模型，开发熵正则化部分最优传输并定义部分混合格罗莫夫-瓦瑟斯坦距离，证明其极小值存在唯一性等性质，经数值实验验证该方法对异常值匹配具有鲁棒性。

Comments 7 figures

2607.01164 2026-07-02 cs.LG 新提交 50%

Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation

基于学习的三维高斯表示对结构化与非结构化体积的高效压缩

Landon Dyken, Sharmistha Chakrabarti, Nathan Debardeleben, Steve Petruzza, Qi Wu, Will Usher, Sidharth Kumar

专题命中 Gaussian Splatting ：novel view synthesis(abstract)

AI总结提出基于三维高斯原语的显式模型压缩体积数据，通过加权聚合重建标量场，无需网格存储，在非结构化体积上全面超越隐式神经表示。

2603.17499 2026-06-02 eess.SY cs.SY eess.SP 50%

A Tutorial on Learning-Based Radio Map Construction: Data, Paradigms, and Physics-Awareness

基于学习的无线电地图构建教程：数据、范式和物理感知

Xiucheng Wang, Yuhao Pan, Nan Cheng, Çağkan Yapar, Ruijin Sun, Zhisheng Yin, Conghao Zhou, Wenchao Xu, Yuxiang Zhang, Jianhua Zhang, Shuguang Cui, Xuemin Shen

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)

AI总结本文系统综述了基于学习的无线电地图构建方法，从数据、范式和物理感知三个维度展开，并讨论了未来研究方向。

2605.18866 2026-05-27 cs.LG cs.AI 50%

FLUIDSPLAT: Reconstructing Physical Fields from Sparse Sensors via Gaussian Primitives

FLUIDSPLAT: 通过高斯原语从稀疏传感器重建物理场

Huaxi Huang, Meng Li, Zhengqing Gao, Xi Zhou, Xiaoshui Huang, Xiao Sun

机构 * Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； The Hong Kong University of Science and Technology（香港科学与技术大学）； Mohamed bin Zayed University of Artificial Intelligence（莫扎德·本·扎耶德人工智能大学）； Shanghai Jiaotong University（上海交通大学）

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)

AI总结提出FLUIDSPLAT模型，利用高斯原语作为空间显式中间表示，从稀疏传感器数据重建流场，理论分析了表示能力与观测数的关系，并在多个基准上实现误差降低11-28%。

Comments 24 pages, 5 figures,preprint

2604.19493 2026-04-22 stat.ME stat.CO 50%

A Nonparametric Goodness-of-Fit Test for High-Dimensional Generalized Gaussian Distributions via Nearest-Neighbor Graphs

基于最近邻图的高维广义高斯分布 goodness-of-fit 非参数检验

Mehmet Sıddık Çadırcı, Yener Ünal

专题命中 Gaussian Splatting ：point cloud(abstract)

AI总结本文提出基于最近邻图和适应性零原理的非参数检验方法，用于评估高维广义高斯分布模型的拟合优度，通过稳健标准化和交叉边计数实现，具有高维扩展性和几何解释。

Comments 22 pages, 5 pages

2509.10415 2026-04-13 math.NA cs.NA 50%

Multiscaling in Wasserstein Spaces

Wael Mattar, Nir Sharon

专题命中 Gaussian Splatting ：point cloud(abstract)

2604.07086 2026-04-09 eess.SP 50%

Radio-Frequency Inverse Rendering for Wireless Environment Modeling

无线环境建模的射频逆渲染

Fuhai Wang, Zihan Jin, Lehang Wang, Xuehui Dong, Tiebin Mi, Robert Caiming Qiu, Zenan ling

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)

AI总结本文提出一种物理基础的射频逆渲染框架，通过分离射频发射、几何和材料电磁特性，提升无线环境建模的精度与灵活性。

2603.20656 2026-03-24 stat.ML cs.AI cs.LG math.OC math.ST stat.TH 50%

Sinkhorn Based Associative Memory Retrieval Using Spherical Hellinger Kantorovich Dynamics

基于Sinkhorn的关联记忆检索使用球面Hellinger Kantorovich动力学

Aratrika Mustafi, Soumya Mukherjee

专题命中 Gaussian Splatting ：point cloud(abstract)

AI总结本文提出基于Sinkhorn的关联记忆检索方法，利用球面Hellinger Kantorovich动力学实现抗扰动恢复，通过几何收敛性和盆地不变性提升存储模式的稳定性与恢复能力。

2509.20508 2026-03-04 stat.ML cs.LG 50%

Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein Distances

通过回归切片Wasserstein距离快速估计Wasserstein距离

Khai Nguyen, Hai Nguyen, Nhat Ho

机构 * Department of Statistics and Data Sciences University of Texas at Austin（统计与数据科学系得克萨斯大学奥斯汀分校）

专题命中 Gaussian Splatting ：point cloud(abstract)

AI总结本文提出通过回归切片Wasserstein距离快速估计Wasserstein距离的方法，该方法在多种任务中表现出色，尤其在低数据情况下优于现有模型。

Comments Accepted to ICLR 2026, 34 pages, 30 figures, 6 tables

2510.05930 2026-03-02 cs.LG cs.AI math.DG 50%

Carré du champ flow matching: better quality-generalisation tradeoff in generative models

Carré du champ flow matching: 更好的质量-泛化权衡在生成模型中

Jacob Bamberger, Iolo Jones, Dennis Duncan, Michael M. Bronstein, Pierre Vandergheynst, Adam Gosztolai

机构 * Institute of Artificial Intelligence（人工智能研究所）； Medical University of Vienna（维也纳医科大学）； University of Oxford（牛津大学）； AITHYRA ； EPFL（苏黎世联邦理工学院）

专题命中 Gaussian Splatting ：point cloud(abstract)

AI总结 Carré du champ flow matching通过几何感知噪声改进生成模型的质量-泛化权衡，适用于数据稀缺和非均匀采样场景。

2601.18985 2026-01-29 math.AT 50%

Reliable Topology for Dynamic Data: Mathematical Foundations and Applications

动态数据的可靠拓扑：数学基础与应用

Chad M. Topaz

专题命中 Gaussian Splatting ：point cloud(abstract)

AI总结本文提出了一种条件稳定性理论，为动态数据中的Crocker图提供精确不变性和有限变化保障，揭示了稳定性阈值与几何关系。

2503.08305 2026-01-27 cs.LG physics.chem-ph physics.comp-ph 50%

ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitals

ELECTRA：一种用于3D电荷密度预测的笛卡尔网络

Jonas Elsborg, Luca Thiede, Alán Aspuru-Guzik, Tejs Vegge, Arghya Bhowmik

机构 * Technical University of Denmark（丹麦技术大学）； CAPeX Pioneer Center for Accelerating P2X Materials Discovery（CAPeX先锋中心）； University of Toronto（多伦多大学）； Vector Institute for Artificial Intelligence（人工智能矢量研究所）； Canadian Institute for Advanced Research (CIFAR)（加拿大高级研究 institute）

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)

AI总结 ELECTRA通过笛卡尔张量网络预测漂浮轨道位置，实现高效且准确的3D电荷密度预测，并显著降低DFT计算的SCF迭代次数。

Comments 10 pages, 4 figures, 5 tables, NeurIPS 2025

2511.14042 2025-11-19 stat.ML cs.LG math.OC 50%

Splat Regression Models

Mara Daniels, Philippe Rigollet

机构 * MIT Mathematics（麻省理工学院数学系）

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)

2410.23220 2025-11-18 math.ST math.OC stat.TH 50%

Method of Moments for Estimation of Noisy Curves

Phillip Lo, Yuehaw Khoo

专题命中 Gaussian Splatting ：point cloud(abstract)

Comments To appear in SIAM Journal on Mathematics of Data Science

2511.04944 2025-11-10 eess.SP 50%

Channel Knowledge Map Construction: Recent Advances and Open Challenges

Zixiang Ren, Juncong Zhou, Jie Xu, Ling Qiu, Yong Zeng, Han Hu, Juyong Zhang, Rui Zhang

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)

2510.13978 2025-10-24 cs.CG 50%

Instant Skinned Gaussian Avatars for Web, Mobile and VR Applications

Naruya Kondo, Yuto Asano, Yoichi Ochiai

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)

Comments Accepted to SUI 2025 Demo Track

2504.07144 2025-08-26 eess.IV 50%

GIGA: Generalizable Sparse Image-driven Gaussian Humans

Anton Zubekhin, Heming Zhu, Paulo Gotardo, Thabo Beeler, Marc Habermann, Christian Theobalt

专题命中 Gaussian Splatting ：novel view synthesis(abstract)

Comments 15 pages, 10 figures, project page: https://vcai.mpi-inf.mpg.de/projects/GIGA

2507.19835 2025-07-29 cs.SD cs.MM 50%

SonicGauss: Position-Aware Physical Sound Synthesis for 3D Gaussian Representations

Chunshi Wang, Hongxing Li, Yawei Luo

机构 * Zhejiang University（浙江大学）

专题命中 Gaussian Splatting ：3DGS(abstract)

Comments Accepted by ACMMM'25

2506.15948 2025-06-23 cs.IT eess.IV math.IT 50%

Information-computation trade-offs in non-linear transforms

Connor Ding, Abhiram Rao Gorle, Jiwon Jeong, Naomi Sagan, Tsachy Weissman

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)

Comments Authors listed in alphabetical order of last name

2506.02929 2025-06-04 cs.AR 50%

Large Processor Chip Model

Kaiyan Chang, Mingzhi Chen, Yunji Chen, Zhirong Chen, Dongrui Fan, Junfeng Gong, Nan Guo, Yinhe Han, Qinfen Hao, Shuo Hou, Xuan Huang, Pengwei Jin, Changxin Ke, Cangyuan Li, Guangli Li, Huawei Li, Kuan Li, Naipeng Li, Shengwen Liang, Cheng Liu, Hongwei Liu, Jiahua Liu, Junliang Lv, Jianan Mu, Jin Qin, Bin Sun, Chenxi Wang, Duo Wang, Mingjun Wang, Ying Wang, Chenggang Wu, Peiyang Wu, Teng Wu, Xiao Xiao, Mengyao Xie, Chenwei Xiong, Ruiyuan Xu, Mingyu Yan, Xiaochun Ye, Kuai Yu, Rui Zhang, Shuoming Zhang, Jiacheng Zhao

专题命中 Gaussian Splatting ：Gaussian Splatting(abstract)

2405.15506 2025-05-21 cs.LG 50%

Learning to Discretize Denoising Diffusion ODEs

Vinh Tong, Hoang Trung-Dung, Anji Liu, Guy Van den Broeck, Mathias Niepert

专题命中 Gaussian Splatting ：point cloud(abstract)

2405.04804 2025-04-08 cs.NI 50%

WixUp: A General Data Augmentation Framework for Wireless Perception in Tracking of Humans

Yin Li, Rajalakshmi Nandakumar

专题命中 Gaussian Splatting ：point cloud(abstract)

Comments SenSys pre-published version

2412.04286 2024-12-06 math.ST math.AT stat.TH 50%

Alpha shapes and optimal transport on the sphere

Erik Carlsson, Greg DePaul

专题命中 Gaussian Splatting ：point cloud(abstract)

Comments 21 pages, 3 figures

2409.12805 2024-09-20 stat.ML cs.LG quant-ph 50%

Robust estimation of the intrinsic dimension of data sets with quantum cognition machine learning

Luca Candelori, Alexander G. Abanov, Jeffrey Berger, Cameron J. Hogan, Vahagn Kirakosyan, Kharen Musaelian, Ryan Samson, James E. T. Smith, Dario Villani, Martin T. Wells, Mengjia Xu

专题命中 Gaussian Splatting ：point cloud(abstract)

2311.17831 2024-05-02 math.ST stat.TH 50%

Confidence Regions for Filamentary Structures

Wanli Qiao

专题命中 Gaussian Splatting ：point cloud(abstract)

2210.10962 2023-11-10 stat.ML cs.LG math.OC 50%

Optimization on Manifolds via Graph Gaussian Processes

Hwanwoo Kim, Daniel Sanz-Alonso, Ruiyi Yang

专题命中 Gaussian Splatting ：point cloud(abstract)

2310.00049 2023-10-03 hep-ph cs.LG 50%

EPiC-ly Fast Particle Cloud Generation with Flow-Matching and Diffusion

Erik Buhmann, Cedric Ewen, Darius A. Faroughy, Tobias Golling, Gregor Kasieczka, Matthew Leigh, Guillaume Quétant, John Andrew Raine, Debajyoti Sengupta, David Shih

专题命中 Gaussian Splatting ：point cloud(abstract)

Comments 21 pages, 8 figures

2306.14206 2023-06-27 astro-ph.GA astro-ph.SR 50%

Weisfeiler-Lehman Graph Kernel Method: A New Approach to Weak Chemical Tagging

Yuan-Sen Ting, Bhavesh Sharma

专题命中 Gaussian Splatting ：point cloud(abstract)

Comments 7 pages, 4 figures, accepted to the ICML 2023 Machine Learning for Astrophysics workshop

2111.13802 2023-03-03 cs.LG cs.CE 50%

Factorized Fourier Neural Operators

Alasdair Tran, Alexander Mathews, Lexing Xie, Cheng Soon Ong

专题命中 Gaussian Splatting ：point cloud(abstract)

Comments Published in The Eleventh International Conference on Learning Representations (2023). Code is available at https://github.com/alasdairtran/fourierflow

1. Gaussian Splatting 3139 篇

Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians

Entropic Partial Optimal Transport and Partial Gromov--Wasserstein Distance between Gaussian Mixtures

Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representation

A Tutorial on Learning-Based Radio Map Construction: Data, Paradigms, and Physics-Awareness

FLUIDSPLAT: Reconstructing Physical Fields from Sparse Sensors via Gaussian Primitives

A Nonparametric Goodness-of-Fit Test for High-Dimensional Generalized Gaussian Distributions via Nearest-Neighbor Graphs

Multiscaling in Wasserstein Spaces

Radio-Frequency Inverse Rendering for Wireless Environment Modeling

Sinkhorn Based Associative Memory Retrieval Using Spherical Hellinger Kantorovich Dynamics

Fast Estimation of Wasserstein Distances via Regression on Sliced Wasserstein Distances

Carré du champ flow matching: better quality-generalisation tradeoff in generative models

Reliable Topology for Dynamic Data: Mathematical Foundations and Applications

ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitals

Splat Regression Models

Method of Moments for Estimation of Noisy Curves

Channel Knowledge Map Construction: Recent Advances and Open Challenges

Instant Skinned Gaussian Avatars for Web, Mobile and VR Applications

GIGA: Generalizable Sparse Image-driven Gaussian Humans

SonicGauss: Position-Aware Physical Sound Synthesis for 3D Gaussian Representations

Information-computation trade-offs in non-linear transforms

Large Processor Chip Model

Learning to Discretize Denoising Diffusion ODEs

WixUp: A General Data Augmentation Framework for Wireless Perception in Tracking of Humans

Alpha shapes and optimal transport on the sphere

Robust estimation of the intrinsic dimension of data sets with quantum cognition machine learning

Confidence Regions for Filamentary Structures

Optimization on Manifolds via Graph Gaussian Processes

EPiC-ly Fast Particle Cloud Generation with Flow-Matching and Diffusion

Weisfeiler-Lehman Graph Kernel Method: A New Approach to Weak Chemical Tagging

Factorized Fourier Neural Operators