3D 视觉

PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction

PointNSP: 通过下一尺度细节预测实现自回归3D点云生成

Ziqiao Meng, Qichao Wang, Zhiyang Dou, Zixing Song, Zhipeng Zhou, Irwin King, Peilin Zhao

机构 * National University of Singapore（新加坡国立大学） ； Nanyang Technological University（南洋理工大学） ； University of Hong Kong（香港大学） ； University of Cambridge（剑桥大学） ； The Chinese University of Hong Kong（香港中文大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

专题命中 点云 ：point cloud(title,abstract)；分类 cs.CV

AI总结 PointNSP通过下一尺度细节预测实现自回归3D点云生成，首次在自回归范式中达到最先进的生成质量，并在参数、训练和推理效率上超越扩散基线。

Comments 24 pages; Previously this version appeared as arXiv:2510.05613 which was submitted as a new work by accident

STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset

STPLS3D: 一种大规模合成与真实空摄影测量3D点云数据集

Meida Chen, Qingyong Hu, Zifan Yu, Hugues Thomas, Andrew Feng, Yu Hou, Kyle McCullough, Fengbo Ren, Lucio Soibelman

专题命中 点云 ：point cloud(title,abstract)；分类 cs.CV

AI总结 STPLS3D通过程序生成合成3D点云数据，提供大规模标注的空摄影测量数据集，包含16平方公里景观和18种细粒度语义类别，有效解决大规模数据采集与标注的挑战。

Journal ref https://bmvc2022.mpi-inf.mpg.de/429/

OpenBox: Annotate Any Bounding Boxes in 3D

OpenBox: 任意3D边界框的标注

In-Jae Lee, Mungyeom Kim, Kwonyoung Ryu, Pierre Musacchio, Jaesik Park

机构 * Seoul National University（首尔国立大学） ； POSTECH 纠错

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

AI总结 OpenBox通过2D视觉基础模型实现无需自我训练的高质量3D边界框标注，提升自动驾驶中物体检测的准确性和效率。

Comments Accepted by NeurIPS 2025

LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures

LiNeXt：重新审视基于高效非扩散架构的LiDAR补全

Wenzhe He, Xiaojun Chen, Ruiqi Wang, Ruihui Li, Huilong Pi, Jiapeng Zhang, Zhuo Tang, Kenli Li

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

AI总结 LiNeXt通过高效非扩散架构实现快速准确的LiDAR点云补全，提升实时性能并减少计算开销。

Comments 18 pages, 13 figures, Accepted to AAAI 2026

PETAR: Localized Findings Generation with Mask-Aware Vision-Language Modeling for PET Automated Reporting

PETAR：基于掩码感知的视觉-语言建模的局部发现生成用于PET自动报告

Danyal Maqbool, Changhee Lee, Zachary Huemann, Samuel D. Church, Matthew E. Larson, Scott B. Perlman, Tomas A. Romero, Joshua D. Warner, Meghan Lubner, Xin Tie, Jameson Merkow, Junjie Hu, Steve Y. Cho, Tyler J. Bradshaw

机构 * University of Wisconsin–Madison Department of Computer Sciences（威斯康星大学麦迪逊分校计算机科学系） ； University of Wisconsin–Madison Department Radiology（威斯康星大学麦迪逊分校放射学系） ； Microsoft（微软公司） 纠错

专题命中 点云 ：3D vision(abstract)；分类 cs.CV

AI总结 PETAR通过引入PETARSeg-11K数据集和PETAR-4B模型，实现基于掩码感知的3D PET自动报告生成，提升医学影像分析的精度与实用性。

New Spiking Architecture for Multi-Modal Decision-Making in Autonomous Vehicles

多模态决策中自动驾驶车辆的新脉冲架构

Aref Ghoreishee, Abhishek Mishra, Lifeng Zhou, John Walsh, Nagarajan Kandasamy

机构 * Electrical and Computer Engineering Department（电子与计算机工程系） 纠错

专题命中 点云 ：point cloud(abstract)

AI总结 本文提出了一种基于脉冲神经元的高效多模态决策架构，用于提升自动驾驶车辆的实时决策能力。

VSRD++: Autolabeling for 3D Object Detection via Instance-Aware Volumetric Silhouette Rendering

VSRD++: 通过实例感知的体素轮廓渲染实现3D目标检测的自标注

Zihua Liu, Hiroki Sakuma, Masatoshi Okutomi

机构 * Department of System and Control Engineering, Institute of Science Tokyo, Tokyo（系统与控制工程系，科学东京研究所） 纠错

专题命中 新视角合成 ：point cloud(abstract)；分类 cs.CV

AI总结 VSRD++通过实例感知的体素轮廓渲染技术实现单目3D目标检测的弱监督自标注，有效提升静态和动态场景下的检测性能。

Comments arXiv admin note: text overlap with arXiv:2404.00149

Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer

Gemini Robotics 1.5：通过先进的具身推理、思考和运动转移推动通用机器人前沿

Gemini Robotics Team, Abbas Abdolmaleki, Saminda Abeyruwan, Joshua Ainslie, Jean-Baptiste Alayrac, Montserrat Gonzalez Arenas, Ashwin Balakrishna, Nathan Batchelor, Alex Bewley, Jeff Bingham, Michael Bloesch, Konstantinos Bousmalis, Philemon Brakel, Anthony Brohan, Thomas Buschmann, Arunkumar Byravan, Serkan Cabi, Ken Caluwaerts, Federico Casarini, Christine Chan, Oscar Chang, London Chappellet-Volpini, Jose Enrique Chen, Xi Chen, Hao-Tien Lewis Chiang, Krzysztof Choromanski, Adrian Collister, David B. D'Ambrosio, Sudeep Dasari, Todor Davchev, Meet Kirankumar Dave, Coline Devin, Norman Di Palo, Tianli Ding, Carl Doersch, Adil Dostmohamed, Yilun Du, Debidatta Dwibedi, Sathish Thoppay Egambaram, Michael Elabd, Tom Erez, Xiaolin Fang, Claudio Fantacci, Cody Fong, Erik Frey, Chuyuan Fu, Ruiqi Gao, Marissa Giustina, Keerthana Gopalakrishnan, Laura Graesser, Oliver Groth, Agrim Gupta, Roland Hafner, Steven Hansen, Leonard Hasenclever, Sam Haves, Nicolas Heess, Brandon Hernaez, Alex Hofer, Jasmine Hsu, Lu Huang, Sandy H. Huang, Atil Iscen, Mithun George Jacob, Deepali Jain, Sally Jesmonth, Abhishek Jindal, Ryan Julian, Dmitry Kalashnikov, M. Emre Karagozler, Stefani Karp, Matija Kecman, J. Chase Kew, Donnie Kim, Frank Kim, Junkyung Kim, Thomas Kipf, Sean Kirmani, Ksenia Konyushkova, Li Yang Ku, Yuheng Kuang, Thomas Lampe, Antoine Laurens, Tuan Anh Le, Isabel Leal, Alex X. Lee, Tsang-Wei Edward Lee, Guy Lever, Jacky Liang, Li-Heng Lin, Fangchen Liu, Shangbang Long, Caden Lu, Sharath Maddineni, Anirudha Majumdar, Kevis-Kokitsi Maninis, Andrew Marmon, Sergio Martinez, Assaf Hurwitz Michaely, Niko Milonopoulos, Joss Moore, Robert Moreno, Michael Neunert, Francesco Nori, Joy Ortiz, Kenneth Oslund, Carolina Parada, Emilio Parisotto, Amaris Paryag, Acorn Pooley, Thomas Power, Alessio Quaglino, Haroon Qureshi, Rajkumar Vasudeva Raju, Helen Ran, Dushyant Rao, Kanishka Rao, Isaac Reid, David Rendleman, Krista Reymann, Miguel Rivas, Francesco Romano, Yulia Rubanova, Peter Pastor Sampedro, Pannag R Sanketi, Dhruv Shah, Mohit Sharma, Kathryn Shea, Mohit Shridhar, Charles Shu, Vikas Sindhwani, Sumeet Singh, Radu Soricut, Rachel Sterneck, Ian Storz, Razvan Surdulescu, Jie Tan, Jonathan Tompson, Saran Tunyasuvunakool, Jake Varley, Grace Vesom, Giulia Vezzani, Maria Bauza Villalonga, Oriol Vinyals, René Wagner, Ayzaan Wahid, Stefan Welker, Paul Wohlhart, Chengda Wu, Markus Wulfmeier, Fei Xia, Ted Xiao, Annie Xie, Jinyu Xie, Peng Xu, Sichun Xu, Ying Xu, Zhuo Xu, Jimmy Yan, Sherry Yang, Skye Yang, Yuxiang Yang, Hiu Hong Yu, Wenhao Yu, Wentao Yuan, Yuan Yuan, Jingwei Zhang, Tingnan Zhang, Zhiyuan Zhang, Allan Zhou, Guangyao Zhou, Yuxiang Zhou

专题命中 空间理解 ：spatial understanding(abstract)；分类 cs.RO

AI总结 Gemini Robotics 1.5通过具身推理、思考和运动转移技术，提升通用机器人在复杂任务中的能力。

ADA-DPM: A Neural Descriptors-based Adaptive Noise Filtering Strategy for SLAM

ADA-DPM: 基于神经描述符的自适应噪声过滤策略用于SLAM

Yongxin Shao, Aihong Tan, Binrui Wang, Yinlian Jin, Licong Guan, Peng Liao

机构 * College of Metrology Measurement and Instrument（计量测量与仪器学院） ； College of Mechanical and Electrical Engineering（机械与电气工程学院） 纠错

专题命中 SLAM与定位 ：point cloud(abstract)；分类 cs.RO

AI总结 ADA-DPM通过动态分割、全局重要性评分和跨层图卷积模块，提升SLAM中动态物体干扰和噪声的鲁棒性。