3D 视觉

OT-MeanFlow3D: Bridging Optimal Transport and Meanflow for Efficient 3D Point Cloud Generation

OT-MeanFlow3D: 通过最优传输与Meanflow弥合，实现高效的3D点云生成

Elaheh Akbari, Shansita Sharma, Ping He, Ahmadreza Moradipari, Kyungtae Han, Hamed Pirsiavash, Yikun Bai, Soheil Kolouri

机构 * Department of Computer Science, Vanderbilt University（范德比尔特大学计算机科学系） ； Toyota InfoTech Labs（丰田信息技术实验室） ； Department of Computer Science, University of California, Davis（加州大学戴维斯分校计算机科学系） ； Department of Mathematics, Purdue University（普渡大学数学系） 纠错

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出OT-MeanFlow3D框架，通过整合最优传输采样，提升3D点云生成与修复的效率与准确性，实验表明其在ShapeNet上优于现有基线模型。

Beyond Distance: Quantifying Point Cloud Dynamics with Persistent Homology and Dynamic Optimal Transport

超越距离：利用持久同调和动态最优传输量化点云动态

Yixin Wang, Ting Gao, Jinqiao Duan

机构 * Department of Mathematics and Department of Physics, Great Bay University, Dongguan, China（数学系和物理系，大湾大学，东莞，中国） ； Guangdong Provincial Key Laboratory of Mathematical and Neural Dynamical Systems, Dongguan, China（广东省数学与神经动力系统重点实验室，东莞，中国） 纠错

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出一种框架，通过扩展最近提出的拓扑最优传输（TpOT）距离，分析时间演化点云中的拓扑突变。引入分层动态评估框架，结合拓扑和超图重建策略，通过多尺度指标检测局部重构，验证了运输对齐与多尺度熵诊断结合在动态拓扑分析中的有效性。

Comments 42 pages, 15 figures

Multi-Type Point Cloud Autoencoder: A Complete Equivariant Embedding for Molecule Conformation and Pose

多类型点云自编码器：分子构型和姿态的完整等价嵌入

Michael Kilgour, Mark Tuckerman, Jutta Rogal

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出Mo3ENet，一种用于多类型点云的自编码器，通过新的重构损失实现输入点云的旋转等价嵌入，适用于分子构型和姿态预测。

Task-Oriented Wireless Transmission of 3D Point Clouds: Geometric Versus Semantic Robustness

面向任务的无线3D点云传输：几何鲁棒性与语义鲁棒性

Vukan Ninkovic, Tamara Sobot, Vladimir Vincan, Gorana Gojic, Dragisa Miskovic, Dejan Vukobratovic

机构 * Serbian Ministry of Science, Technological Development and Innovation（塞尔维亚科学技术发展与创新部） ； National Key Research & Development Program of China（中国国家重点研发计划） 纠错

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出面向任务的无线3D点云传输框架，研究几何重建精度与语义鲁棒性在信道干扰下的关系，揭示任务执行无需高精度几何重建的结论。

Comments Submitted to Global 6G Conference 2026

Scalable On-the-fly Transcoding for Adaptive Streaming of Dynamic Point Clouds

动态点云自适应流媒体的可扩展实时转码

Michael Rudolph, Matthias De Fré, Finn Schnier, Tim Wauters, Amr Rizk

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出了一种动态点云流媒体系统，通过实时转码技术降低存储需求并提升并发客户端的可扩展性。

Comments 7 pages, 6 figures

Point Cloud Feature Coding for Object Detection over an Error-Prone Cloud-Edge Collaborative System

点云特征编码用于错误多的云边协作系统中的目标检测

Chongzhen Tian, Hui Yuan, Pan Zhao, Chang Sun, Raouf Hamzaoui, Sam Kwong

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出了一种基于源编码和信道编码的任务驱动点云压缩和可靠传输框架，用于在错误多的云边协作系统中实现高效的目标检测。

Comments 13 pages, 13 figures

FPPS: An FPGA-Based Point Cloud Processing System

FPPS：一种基于FPGA的点云处理系统

Xiaofeng Zhou, Linfeng Du, Hanwei Fan, Wei Zhang

专题命中 点云 ：point cloud(title,abstract)

AI总结 FPPS是一种基于FPGA的点云处理系统，通过优化ICP算法在KITTI数据集上实现了高达35倍的加速，同时保持精度并提升能效。

Topological Signal Processing for 3D Point Cloud Data

拓扑信号处理用于3D点云数据

Tiziana Cattai, Stefania Sardellitti, Stefania Colonnese, Sergio Barbarossa

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出基于拓扑信号处理的3D点云分析方法，通过高阶拉普拉斯算子实现对点云颜色和几何属性的高效处理与重构。

Comments ACCEPTED PAPER TO ICASSP 2026 (IEEE International Conference on Acoustics, Speech, and Signal Processing)

IDSOR: Intensity- and Distance-Aware Statistical Outlier Removal for Weather-Robust LiDAR Point Clouds

IDSOR：基于强度和距离的统计异常点去除用于抗天气的LiDAR点云

Chenyang Yan, Mats Bengtsson

专题命中 点云 ：point cloud(title,abstract)

AI总结 IDSOR通过结合强度和距离信息，有效去除天气引起的LiDAR点云异常点，提升恶劣天气下的点云质量与感知性能。

Lightweight Super Resolution-enabled Coding Model for the JPEG Pleno Learning-based Point Cloud Coding Standard

轻量级超分辨率赋能的编码模型用于基于JPEG Pleno学习的点云编码标准

André F. R. Guarda, Nuno M. M. Rodrigues, Fernando Pereira

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出了一种轻量级超分辨率赋能的点云编码模型，以提高基于JPEG Pleno学习的点云编码标准的压缩效率和实用性。

Comments 32 pages, 8 figures, submitted to Signal Processing: Image Communication

Hint: hierarchical inter-frame correlation for one-shot point cloud sequence compression

提示：用于一次性点云序列压缩的分层帧间相关性

Yuchen Gao, Qi Zhang

专题命中 点云 ：point cloud(title,abstract)

AI总结 HINT通过整合时间和空间相关性，实现了点云序列压缩的高效编码与解码，显著提升了压缩速度和比特率效率。

Comments This paper has been accepted at IEEE ICASSP 2026

Point Cloud Streaming with Latency-Driven Implicit Adaptation using MoQ

基于延迟驱动的隐式适应的点云流媒体使用MoQ

Andrew Freeman, Michael Rudolph, Amr Rizk

专题命中 点云 ：point cloud(title,abstract)

AI总结 本研究提出一种基于延迟驱动的隐式适应方法，利用MoQ协议实现点云流媒体的动态质量调整，根据客户端延迟需求自动优化视频质量。

Persistence-Based Statistics for Detecting Structural Changes in High-Dimensional Point Clouds

基于持续性的统计方法用于检测高维点云中的结构变化

Toshiyuki Nakayama

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出了一种基于持续性的非参数方法，用于检测高维点云中的结构变化，通过持续性景观和詹森-香农散度构建统计量，并证明其稳定性与适用性。

Comments 45 pages, 3 figures, under review

FractalCloud: A Fractal-Inspired Architecture for Efficient Large-Scale Point Cloud Processing

FractalCloud: 一种受分形启发的高效大规模点云处理架构

Yuzhe Fu, Changchun Zhou, Hancheng Ye, Bowen Duan, Qiyu Huang, Chiyue Wei, Cong Guo, Hai "Helen'' Li, Yiran Chen

专题命中 点云 ：point cloud(title,abstract)

AI总结 FractalCloud通过分形启发的架构实现高效大规模点云处理，显著提升速度与能效。

Comments Accepted for publication in HPCA2026. Codes are released at https://github.com/Yuzhe-Fu/FractalCloud

Less Is More: Sparse and Cooperative Perturbation for Point Cloud Attacks

少即是多：用于点云攻击的稀疏与协作扰动

Keke Tang, Tianyu Hao, Xiaofei Wang, Weilong Peng, Denghui Zhang, Peican Zhu, Zhihong Tian

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出SCP框架，通过稀疏且协作的点扰动方法，实现高攻击成功率和更强的对抗效果，适用于点云攻击场景。

Comments Accepted by AAAI'2026 (Oral)

Feature-aware manifold meshing and remeshing of point clouds and polyhedral surfaces with guaranteed smallest edge length

具有特征意识的流形网格生成与重网格化：点云和多边形表面的保证最小边长处理

Henriette Lipschütz, Ulrich Reitebuch, Konrad Polthier, Martin Skrodzki

专题命中 点云 ：point cloud(title,abstract)

AI总结 本文提出了一种从点云生成高质量三角网格的算法，并扩展至处理多边形表面的特征。

Journal ref Proceedings of the 2024 International Meshing Roundtable (IMR); Special Issue of Computer Aided Geometric Design

RCMCL: A Unified Contrastive Learning Framework for Robust Multi-Modal (RGB-D, Skeleton, Point Cloud) Action Understanding

Hasan Akgul, Mari Eplik, Javier Rojas, Akira Yamamoto, Rajesh Kumar, Maya Singh

专题命中 点云 ：point cloud(title,abstract)

Comments 11 pages, 6 figures,

RadarLLM: Empowering Large Language Models to Understand Human Motion from Millimeter-Wave Point Cloud Sequence

Zengyuan Lai, Jiarui Yang, Songpengcheng Xia, Lizhou Lin, Lan Sun, Renwen Wang, Jianran Liu, Qi Wu, Ling Pei

专题命中 点云 ：point cloud(title,abstract)

Comments Accepted by AAAI 2026 (extended version with supplementary materials)

J-SGFT: Joint Spatial and Graph Fourier Domain Learning for Point Cloud Attribute Deblocking

Muhammad Talha, Qi Yang, Zhu Li, Anique Akhtar, Geert Van Der Auwera

专题命中 点云 ：point cloud(title,abstract)

Comments Accepted to ICIP 2025 Workshop on Generative AI for World Simulations and Communications & Celebrating 40 Years of Excellence in Education: Honoring Professor Aggelos Katsaggelos, Sept. 2025, Alaska

Point-Level Topological Representation Learning on Point Clouds

Vincent P. Grande, Michael T. Schaub

机构 * rwth Aachen University（亚琛工业大学） 纠错

专题命中 点云 ：point cloud(title,abstract)

Comments 47 pages, 18 figures, comments welcome

Journal ref International Conference on Machine Learning (ICML 2025)

Fractional harmonic transform on point cloud manifolds

Jiamian Li, Bing-Zhao Li

专题命中 点云 ：point cloud(title,abstract)

Comments Submitted to ICASSP 2026

The Stage Comes to You: A Real-Time Tele-Immersive System with 3D Point Clouds and Vibrotactile Feedback

Takahiro Matsumoto, Takahiro Kusabuka, Hiroshi Chigira, Kazuhiko Murasaki, Kakagu Komazaki, Masafumi Suzuki, Masakatsu Aoki

专题命中 点云 ：point cloud(title,abstract)

Comments 2 pages, 1 figure. Accepted for presentation at SIGGRAPH Asia 2025 Posters. The final version will appear in the ACM Digital Library

Matching the Optimal Denoiser in Point Cloud Diffusion with (Improved) Rotational Alignment

Ameya Daigavane, YuQing Xie, Bodhi P. Vani, Saeed Saremi, Joseph Kleinhenz, Tess Smidt

机构 * Massachusetts Institute of Technology（麻省理工学院） ； Prescient Design, Genentech（Prescient Design，Genentech） 纠错

专题命中 点云 ：point cloud(title,abstract)

Comments under review

On the Impact of LiDAR Point Cloud Compression on Remote Semantic Segmentation

Tiago de S. Fernandes, Ricardo L. de Queiroz

专题命中 点云 ：point cloud(title,abstract)

Comments 5 pages, 8 figures

Generative Design of Crystal Structures by Point Cloud Representations and Diffusion Model

Zhelin Li, Rami Mrad, Runxian Jiao, Guan Huang, Jun Shan, Shibing Chu, Yuanping Chen

专题命中 点云 ：point cloud(title,abstract)

Comments I have submitted to a journal

Journal ref iScience 28, 111659, January 17, 2025

Convexity-Driven Projection for Point Cloud Dimensionality Reduction

Suman Sanyal

机构 * Big Data Analytics, Goa Institute of Management, Goa, India（大数据分析，果阿管理学院，果阿，印度） 纠错

专题命中 点云 ：point cloud(title,abstract)

Checkerboard Target Measurement in Unordered Point Clouds with Coloured ICP

June Moh Goo, Jialun Li, Darmawan Wicaksono, Jan Boehm

专题命中 点云 ：point cloud(title,abstract)

Journal ref The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2025)

A Software-Defined Radio Testbed for Distributed LiDAR Point Cloud Sharing with IEEE 802.11p in V2V Networks

Mario Hernandez, Elijah Bryce, Peter Stubberud, Ebrahim Saberinia, Brendan Morris

专题命中 点云 ：point cloud(title,abstract)

Comments 10 pages, 9 figures

Quantitative homogenization and large-scale regularity of Poisson point clouds

Scott Armstrong, Raghavendra Venkatraman

专题命中 点云 ：point cloud(title,abstract)

Comments 62 pages

Synesthesia of Machines (SoM)-Aided LiDAR Point Cloud Transmission for Collaborative Perception

Ensong Liu, Rongqing Zhang, Xiang Cheng, Jian Tang

专题命中 点云 ：point cloud(title,abstract)