3D 视觉

Real-Time Navigation for Autonomous Aerial Vehicles Using Video

Khizar Anjum, Parul Pandey, Vidyasagar Sadhu, Roberto Tron, Dario Pompili

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

Comments Submitted to Journal of Real-Time Image Processing

Gen-Swarms: Adapting Deep Generative Models to Swarms of Drones

Carlos Plou, Pablo Pueyo, Ruben Martinez-Cantin, Mac Schwager, Ana C. Murillo, Eduardo Montijano

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

Journal ref ECCVW2024 - MAAS Workshop

UGG: Unified Generative Grasping

Jiaxin Lu, Hao Kang, Haoxiang Li, Bo Liu, Yiding Yang, Qixing Huang, Gang Hua

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

Comments 17 pages, 14 figures, ECCV 2024

GAA-TSO: Geometry-Aware Assisted Depth Completion for Transparent and Specular Objects

Yizhe Liu, Tong Jia, Da Cai, Hao Wang, Dongyue Chen

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

HOTFormerLoc: Hierarchical Octree Transformer for Versatile Lidar Place Recognition Across Ground and Aerial Views

Ethan Griffiths, Maryam Haghighat, Simon Denman, Clinton Fookes, Milad Ramezani

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

Comments 16 pages, 13 figures, 10 tables, Accepted to CVPR 2025

LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes

Xiang Xu, Lingdong Kong, Hui Shuai, Liang Pan, Ziwei Liu, Qingshan Liu

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

Comments CVPR 2025; 27 pages, 17 figures, 10 tables; Project Page at https://ldkong.com/LiMoE

SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments

Yinqi Chen, Meiying Zhang, Qi Hao, Guang Zhou

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

Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition

Jiahang Cao, Qiang Zhang, Hanzhong Guo, Jiaxu Wang, Hao Cheng, Renjing Xu

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

Comments Accepted to ICLR 2025 Generative Models for Robot Learning Workshop

VXP: Voxel-Cross-Pixel Large-scale Image-LiDAR Place Recognition

Yun-Jin Li, Mariia Gladkova, Yan Xia, Rui Wang, Daniel Cremers

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

Comments Project page https://yunjinli.github.io/projects-vxp/

DeformPAM: Data-Efficient Learning for Long-horizon Deformable Object Manipulation via Preference-based Action Alignment

Wendi Chen, Han Xue, Fangyuan Zhou, Yuan Fang, Cewu Lu

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

Comments Accepted to ICRA 2025. Project page: https://deform-pam.robotflow.ai

PointVLA: Injecting the 3D World into Vision-Language-Action Models

Chengmeng Li, Junjie Wen, Yan Peng, Yaxin Peng, Feifei Feng, Yichen Zhu

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

TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models

Mark YU, Wenbo Hu, Jinbo Xing, Ying Shan

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

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

Articulated Object Manipulation using Online Axis Estimation with SAM2-Based Tracking

Xi Wang, Tianxing Chen, Qiaojun Yu, Tianling Xu, Zanxin Chen, Yiting Fu, Ziqi He, Cewu Lu, Yao Mu, Ping Luo

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

Comments Project Page: https://hytidel.github.io/video-tracking-for-axis-estimation/

ForestLPR: LiDAR Place Recognition in Forests Attentioning Multiple BEV Density Images

Yanqing Shen, Turcan Tuna, Marco Hutter, Cesar Cadena, Nanning Zheng

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

Comments accepted by CVPR2025

BEVDriver: Leveraging BEV Maps in LLMs for Robust Closed-Loop Driving

Katharina Winter, Mark Azer, Fabian B. Flohr

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

Comments This work has been submitted to the IEEE for possible publication

CSCPR: Cross-Source-Context Indoor RGB-D Place Recognition

Jing Liang, Zhuo Deng, Zheming Zhou, Min Sun, Omid Ghasemalizadeh, Cheng-Hao Kuo, Arnie Sen, Dinesh Manocha

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

ViViDex: Learning Vision-based Dexterous Manipulation from Human Videos

Zerui Chen, Shizhe Chen, Etienne Arlaud, Ivan Laptev, Cordelia Schmid

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

Comments Accepted by ICRA 2025. Project Page: https://zerchen.github.io/projects/vividex.html

CAR-LOAM: Color-Assisted Robust LiDAR Odometry and Mapping

Yufei Lu, Yuetao Li, Zhizhou Jia, Qun Hao, Shaohui Zhang

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

Depth-aware Fusion Method based on Image and 4D Radar Spectrum for 3D Object Detection

Yue Sun, Yeqiang Qian, Chunxiang Wang, Ming Yang

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

Journal ref The 2024 IEEE International Conference on Robotics and Biomimetics (IEEE ROBIO 2024)

Synth It Like KITTI: Synthetic Data Generation for Object Detection in Driving Scenarios

Richard Marcus, Christian Vogel, Inga Jatzkowski, Niklas Knoop, Marc Stamminger

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

Comments Preprint, to appear in ROBOVIS 2025

MambaPlace:Text-to-Point-Cloud Cross-Modal Place Recognition with Attention Mamba Mechanisms

Tianyi Shang, Zhenyu Li, Pengjie Xu, Jinwei Qiao

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

Comments 8 pages

IMM-MOT: A Novel 3D Multi-object Tracking Framework with Interacting Multiple Model Filter

Xiaohong Liu, Xulong Zhao, Gang Liu, Zili Wu, Tao Wang, Lei Meng, Yuhan Wang

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

Comments 8 pages,5 figures

LIR-LIVO: A Lightweight,Robust LiDAR/Vision/Inertial Odometry with Illumination-Resilient Deep Features

Shujie Zhou, Zihao Wang, Xinye Dai, Weiwei Song, Shengfeng Gu

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

EmbodiedSAM: Online Segment Any 3D Thing in Real Time

Xiuwei Xu, Huangxing Chen, Linqing Zhao, Ziwei Wang, Jie Zhou, Jiwen Lu

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

Comments ICLR25 Oral. Project page: https://xuxw98.github.io/ESAM/

Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension

Runwei Guan, Ruixiao Zhang, Ningwei Ouyang, Jianan Liu, Ka Lok Man, Xiaohao Cai, Ming Xu, Jeremy Smith, Eng Gee Lim, Yutao Yue, Hui Xiong

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

Comments Accepted by ICRA 2025

LeAP: Consistent multi-domain 3D labeling using Foundation Models

Simon Gebraad, Andras Palffy, Holger Caesar

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

Comments 9 pages, 4 figures. ICRA25 preprint

Improving Generalization Ability for 3D Object Detection by Learning Sparsity-invariant Features

Hsin-Cheng Lu, Chung-Yi Lin, Winston H. Hsu

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

Comments Accepted to ICRA 2025. Code is available at https://github.com/Tiffamy/3DOD-LSF

INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomy

Nastaran Darabi, Divake Kumar, Sina Tayebati, Amit Ranjan Trivedi

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

LiDAR Loop Closure Detection using Semantic Graphs with Graph Attention Networks

Liudi Yang, Ruben Mascaro, Ignacio Alzugaray, Sai Manoj Prakhya, Marco Karrer, Ziyuan Liu, Margarita Chli

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

Journal ref Journal of Intelligent & Robotic Systems, 2025

SSF-PAN: Semantic Scene Flow-Based Perception for Autonomous Navigation in Traffic Scenarios

Yinqi Chen, Meiying Zhang, Qi Hao, Guang Zhou

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