3D 视觉 - arXivDaily 专题

2312.02208 2023-12-06 cs.CV cs.RO 62%

A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing

Kangcheng Liu

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

Comments International Conference on Robotics and Automation (ICRA) 2022, 6 Figures. arXiv admin note: substantial text overlap with arXiv:2312.01262

2312.01262 2023-12-05 cs.CV cs.RO 62%

A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptors

Kangcheng Liu

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

Comments International Journal of Computer Vision (IJCV), 2022. 10 Figures, 13 Tables

2311.17770 2023-11-30 cs.CV cs.RO 62%

PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection

Weixin Mao, Tiancai Wang, Diankun Zhang, Junjie Yan, Osamu Yoshie

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

2309.00168 2023-11-27 cs.CV cs.RO 62%

Pose-Graph Attentional Graph Neural Network for Lidar Place Recognition

Milad Ramezani, Liang Wang, Joshua Knights, Zhibin Li, Pauline Pounds, Peyman Moghadam

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

Comments 10 pages, 5 figures, 5 tables, Accepted for Publication in the IEEE Robotics and Automation Letters (RA-L)

2311.12562 2023-11-22 cs.CV cs.RO 62%

Multi-Resolution Planar Region Extraction for Uneven Terrains

Yinghan Sun, Linfang Zheng, Hua Chen, Wei Zhang

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

2310.17842 2023-11-16 cs.CV cs.RO 62%

What You See Is What You Detect: Towards better Object Densification in 3D detection

Tianran Liu, Zeping Zhang, Morteza Mousa Pasandi, Robert Laganiere

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

2311.04777 2023-11-09 cs.CV cs.LG cs.RO 62%

Lidar Annotation Is All You Need

Dinar Sharafutdinov, Stanislav Kuskov, Saian Protasov, Alexey Voropaev

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

Comments Preprint, 11 pages

2110.11048 2023-11-08 cs.CV cs.AI cs.RO 62%

K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and Highways

Donghee Paek, Seung-Hyun Kong, Kevin Tirta Wijaya

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

Comments 20 pages, 20 figures, 11 tables

Journal ref 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshop on Autonomous Driving (WAD)

2311.02736 2023-11-07 cs.RO cs.CV 62%

JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds

Saeed Saadatnejad, Yang Gao, Hamid Rezatofighi, Alexandre Alahi

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

2311.01556 2023-11-06 cs.CV cs.RO 62%

MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory

Enxu Li, Sergio Casas, Raquel Urtasun

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

Comments accepted at ICCV 2023

2311.01448 2023-11-03 cs.CV cs.LG cs.RO 62%

UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation

Yuwen Xiong, Wei-Chiu Ma, Jingkang Wang, Raquel Urtasun

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

Comments CVPR 2023. Project page: https://waabi.ai/ultralidar/

2311.00926 2023-11-03 cs.RO cs.AI cs.CV 62%

M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place

Wentao Yuan, Adithyavairavan Murali, Arsalan Mousavian, Dieter Fox

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

Comments 12 pages, 8 figures, accepted by CoRL 2023

2310.16629 2023-10-26 cs.CV cs.RO 62%

EdgeCalib: Multi-Frame Weighted Edge Features for Automatic Targetless LiDAR-Camera Calibration

Xingchen Li, Yifan Duan, Beibei Wang, Haojie Ren, Guoliang You, Yu Sheng, Jianmin Ji, Yanyong Zhang

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

2305.07336 2023-10-20 cs.CV cs.RO 62%

MotionBEV: Attention-Aware Online LiDAR Moving Object Segmentation with Bird's Eye View based Appearance and Motion Features

Bo Zhou, Jiapeng Xie, Yan Pan, Jiajie Wu, Chuanzhao Lu

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

2310.10371 2023-10-17 cs.CV cs.RO 62%

Camera-LiDAR Fusion with Latent Contact for Place Recognition in Challenging Cross-Scenes

Yan Pan, Jiapeng Xie, Jiajie Wu, Bo Zhou

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

2310.07247 2023-10-12 cs.CV cs.RO 62%

Optimizing the Placement of Roadside LiDARs for Autonomous Driving

Wentao Jiang, Hao Xiang, Xinyu Cai, Runsheng Xu, Jiaqi Ma, Yikang Li, Gim Hee Lee, Si Liu

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

2310.06603 2023-10-11 cs.AI cs.CV cs.RO 62%

V2X-AHD:Vehicle-to-Everything Cooperation Perception via Asymmetric Heterogenous Distillation Network

Caizhen He, Hai Wang, Long Chen, Tong Luo, Yingfeng Cai

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

2302.01665 2023-10-09 cs.CV cs.RO 62%

CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data

Junyi Ma, Guangming Xiong, Jingyi Xu, Xieyuanli Chen

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

Comments accepted by IEEE Transactions on Industrial Informatics 2023

2209.14941 2023-10-09 cs.CV cs.RO 62%

EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding

Yanmin Wu, Xinhua Cheng, Renrui Zhang, Zesen Cheng, Jian Zhang

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

Comments CVPR2023, with supplementary material

Journal ref 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, 2023, pp. 19231-19242

2309.13549 2023-10-03 cs.RO cs.CV 62%

Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset

Arthur Zhang, Chaitanya Eranki, Christina Zhang, Ji-Hwan Park, Raymond Hong, Pranav Kalyani, Lochana Kalyanaraman, Arsh Gamare, Arnav Bagad, Maria Esteva, Joydeep Biswas

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

Comments 19 pages, 18 figures, 12 tables

2309.16870 2023-10-02 cs.CV cs.LG cs.RO 62%

LEF: Late-to-Early Temporal Fusion for LiDAR 3D Object Detection

Tong He, Pei Sun, Zhaoqi Leng, Chenxi Liu, Dragomir Anguelov, Mingxing Tan

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

2307.01462 2023-09-20 cs.RO cs.CV 62%

Practical Collaborative Perception: A Framework for Asynchronous and Multi-Agent 3D Object Detection

Minh-Quan Dao, Julie Stephany Berrio, Vincent Frémont, Mao Shan, Elwan Héry, Stewart Worrall

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

Comments The code is available at https://github.com/quan-dao/practical-collab-perception

2309.08086 2023-09-18 cs.RO cs.AI cs.CV cs.LG 62%

Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM

Chenghao Shi, Xieyuanli Chen, Junhao Xiao, Bin Dai, Huimin Lu

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

Comments 20 pages 10 figures 7 tables

2309.01925 2023-09-06 cs.CV cs.RO 62%

DR-Pose: A Two-stage Deformation-and-Registration Pipeline for Category-level 6D Object Pose Estimation

Lei Zhou, Zhiyang Liu, Runze Gan, Haozhe Wang, Marcelo H. Ang

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

Comments Camera-ready version accepted to IROS 2023

2303.05367 2023-09-06 cs.CV cs.RO 62%

Rethinking Range View Representation for LiDAR Segmentation

Lingdong Kong, Youquan Liu, Runnan Chen, Yuexin Ma, Xinge Zhu, Yikang Li, Yuenan Hou, Yu Qiao, Ziwei Liu

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

Comments ICCV 2023; 24 pages, 10 figures, 14 tables; Webpage at https://ldkong.com/RangeFormer

2207.00026 2023-09-04 cs.CV cs.LG cs.RO 62%

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

Lingdong Kong, Jiawei Ren, Liang Pan, Ziwei Liu

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

Comments CVPR 2023 (Highlight); 27 pages, 11 figures, 12 tables; Code at https://github.com/ldkong1205/LaserMix

2308.16893 2023-09-01 cs.RO cs.AI cs.CV cs.LG 62%

Language-Conditioned Path Planning

Amber Xie, Youngwoon Lee, Pieter Abbeel, Stephen James

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

Comments Conference on Robot Learning, 2023

2308.16528 2023-09-01 cs.CV cs.LG cs.RO 62%

SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects

Ning Gao, Ngo Anh Vien, Hanna Ziesche, Gerhard Neumann

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

Journal ref Conference on Robot Learning (CoRL), 2023

2308.10115 2023-08-22 cs.MM cs.GR cs.RO 62%

An Evaluation of Three Distance Measurement Technologies for Flying Light Specks

Trung Phan, Hamed Alimohammadzadeh, Heather Culbertson, Shahram Ghandeharizadeh

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

Comments In International Conference on Intelligent Metaverse Technologies and Applications (iMETA2023), Tartu, Estonia, September 18-20, 2023

2307.15671 2023-07-31 cs.CV cs.RO 62%

TrackAgent: 6D Object Tracking via Reinforcement Learning

Konstantin Röhrl, Dominik Bauer, Timothy Patten, Markus Vincze

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

Comments International Conference on Computer Vision Systems (ICVS) 2023

1. 点云 7723 篇

A Data-efficient Framework for Robotics Large-scale LiDAR Scene Parsing

A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptors

PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection

Pose-Graph Attentional Graph Neural Network for Lidar Place Recognition

Multi-Resolution Planar Region Extraction for Uneven Terrains

What You See Is What You Detect: Towards better Object Densification in 3D detection

Lidar Annotation Is All You Need

K-Lane: Lidar Lane Dataset and Benchmark for Urban Roads and Highways

JRDB-Traj: A Dataset and Benchmark for Trajectory Forecasting in Crowds

MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory

UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generation

M2T2: Multi-Task Masked Transformer for Object-centric Pick and Place

EdgeCalib: Multi-Frame Weighted Edge Features for Automatic Targetless LiDAR-Camera Calibration

MotionBEV: Attention-Aware Online LiDAR Moving Object Segmentation with Bird's Eye View based Appearance and Motion Features

Camera-LiDAR Fusion with Latent Contact for Place Recognition in Challenging Cross-Scenes

Optimizing the Placement of Roadside LiDARs for Autonomous Driving

V2X-AHD:Vehicle-to-Everything Cooperation Perception via Asymmetric Heterogenous Distillation Network

CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data

EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding

Towards Robust Robot 3D Perception in Urban Environments: The UT Campus Object Dataset

LEF: Late-to-Early Temporal Fusion for LiDAR 3D Object Detection

Practical Collaborative Perception: A Framework for Asynchronous and Multi-Agent 3D Object Detection

Fast and Accurate Deep Loop Closing and Relocalization for Reliable LiDAR SLAM

DR-Pose: A Two-stage Deformation-and-Registration Pipeline for Category-level 6D Object Pose Estimation

Rethinking Range View Representation for LiDAR Segmentation

LaserMix for Semi-Supervised LiDAR Semantic Segmentation

Language-Conditioned Path Planning

SA6D: Self-Adaptive Few-Shot 6D Pose Estimator for Novel and Occluded Objects

An Evaluation of Three Distance Measurement Technologies for Flying Light Specks

TrackAgent: 6D Object Tracking via Reinforcement Learning