3D 视觉 - arXivDaily 专题

2208.05962 2022-08-12 cs.CV cs.LG 79%

PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees

Jun-Kun Chen, Yu-Xiong Wang

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

Comments ECCV 2022

2208.05216 2022-08-11 cs.CV 79%

Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer

Zhipeng Luo, Changqing Zhou, Liang Pan, Gongjie Zhang, Tianrui Liu, Yueru Luo, Haiyu Zhao, Ziwei Liu, Shijian Lu

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

Comments arXiv admin note: substantial text overlap with arXiv:2112.02857

2201.02726 2022-08-10 cs.CV 79%

Real-time Rail Recognition Based on 3D Point Clouds

Xinyi Yu, Weiqi He, Xuecheng Qian, Yang Yang, Linlin Ou

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

2208.04510 2022-08-10 cs.CV 79%

Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching

Yikai Bian, Le Hui, Jianjun Qian, Jin Xie

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

2208.04309 2022-08-09 cs.CV 79%

3D Vision with Transformers: A Survey

Jean Lahoud, Jiale Cao, Fahad Shahbaz Khan, Hisham Cholakkal, Rao Muhammad Anwer, Salman Khan, Ming-Hsuan Yang

专题命中点云：3D vision(title,abstract)；分类 cs.CV

2208.03791 2022-08-09 cs.CV 79%

Global Hierarchical Attention for 3D Point Cloud Analysis

Dan Jia, Alexander Hermans, Bastian Leibe

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

Comments Accepted to the German Conference on Pattern Recognition (GCPR) 2022

2207.10859 2022-08-09 cs.CV 79%

Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter

Tuan Ngo, Khoi Nguyen

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

Comments Accepted to ECCV 2022

2208.02716 2022-08-05 eess.IV cs.CV 79%

IT/IST/IPLeiria Response to the Call for Proposals on JPEG Pleno Point Cloud Coding

André F. R. Guarda, Nuno M. M. Rodrigues, Manuel Ruivo, Luís Coelho, Abdelrahman Seleem, Fernando Pereira

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

Comments 52 pages, 8 figures. Document submitted to the 96th ISO/IEC JTC 1/SC 29/WG 1 (JPEG) meeting

2208.02519 2022-08-05 cs.CV cs.IT cs.MM eess.IV math.IT 79%

IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compression

Kang You, Pan Gao, Qing Li

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

Comments 12 pages

2208.01925 2022-08-04 cs.CV 79%

SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud

Xiangrui Zhao, Sheng Yang, Tianxin Huang, Jun Chen, Teng Ma, Mingyang Li, Yong Liu

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

Comments 17 pages, ECCV 2022 Accepted

2208.00524 2022-08-02 cs.CV cs.AI 79%

CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning

Mahdi Saleh, Yige Wang, Nassir Navab, Benjamin Busam, Federico Tombari

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

2208.00223 2022-08-02 cs.CV cs.AI cs.LG 79%

PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds

Aoran Xiao, Jiaxing Huang, Dayan Guan, Kaiwen Cui, Shijian Lu, Ling Shao

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

2203.11183 2022-08-02 cs.CV 79%

Masked Discrimination for Self-Supervised Learning on Point Clouds

Haotian Liu, Mu Cai, Yong Jae Lee

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

Comments ECCV 2022; Code: https://github.com/haotian-liu/MaskPoint

2207.14268 2022-07-29 cs.CV 79%

MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud

Michaël Ramamonjisoa, Sinisa Stekovic, Vincent Lepetit

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

Comments Accepted at ECCV 2022. Project page: https://michaelramamonjisoa.github.io/projects/MonteBoxFinder, Code: https://github.com/MichaelRamamonjisoa/MonteBoxFinder

2207.12984 2022-07-27 cs.CV 79%

Explaining Deep Neural Networks for Point Clouds using Gradient-based Visualisations

Jawad Tayyub, Muhammad Sarmad, Nicolas Schönborn

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

2207.11995 2022-07-27 cs.CV 79%

3D Siamese Transformer Network for Single Object Tracking on Point Clouds

Le Hui, Lingpeng Wang, Linghua Tang, Kaihao Lan, Jin Xie, Jian Yang

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

Comments Accepted to ECCV'22

2207.07016 2022-07-27 cs.CV 79%

Accurate Ground-Truth Depth Image Generation via Overfit Training of Point Cloud Registration using Local Frame Sets

Jiwan Kim, Minchang Kim, Yeong-Gil Shin, Minyoung Chung

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

Comments 10 pages, 7 figures

2207.12394 2022-07-26 cs.CV 79%

Dynamic 3D Scene Analysis by Point Cloud Accumulation

Shengyu Huang, Zan Gojcic, Jiahui Huang, Andreas Wieser, Konrad Schindler

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

Comments ECCV 2022, camera ready

2207.11889 2022-07-26 cs.CV 79%

Salient Object Detection for Point Clouds

Songlin Fan, Wei Gao, Ge Li

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

Comments Accepted to ECCV 2022. Project Page: https://git.openi.org.cn/OpenPointCloud/PCSOD

2203.05940 2022-07-26 cs.CV 79%

PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

Aihua Mao, Zihui Du, Yu-Hui Wen, Jun Xuan, Yong-Jin Liu

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

2109.00182 2022-07-26 cs.CV 79%

You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors

Haiping Wang, Yuan Liu, Zhen Dong, Wenping Wang

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

Comments Accepted by ACM Multimedia(MM) 2022, Project page: https://hpwang-whu.github.io/YOHO/

2104.09035 2022-07-26 cs.CV 79%

Lidar Point Cloud Guided Monocular 3D Object Detection

Liang Peng, Fei Liu, Zhengxu Yu, Senbo Yan, Dan Deng, Zheng Yang, Haifeng Liu, Deng Cai

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

Comments ECCV 2022

2207.11484 2022-07-26 cs.CV 79%

GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation

Keqiang Li, Mingyang Zhao, Huaiyu Wu, Dong-Ming Yan, Zhen Shen, Fei-Yue Wang, Gang Xiong

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

2205.15225 2022-07-25 cs.CV 79%

Few-shot Class-incremental Learning for 3D Point Cloud Objects

Townim Chowdhury, Ali Cheraghian, Sameera Ramasinghe, Sahar Ahmadi, Morteza Saberi, Shafin Rahman

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

2207.10315 2022-07-22 cs.CV 79%

SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer

Haoran Zhou, Yun Cao, Wenqing Chu, Junwei Zhu, Tong Lu, Ying Tai, Chengjie Wang

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

Comments Camera-ready, to be published in ECCV 2022, with supplementary material

2207.10278 2022-07-22 cs.CV 79%

Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification

Yongqiang Mao, Kaiqiang Chen, Wenhui Diao, Xian Sun, Xiaonan Lu, Kun Fu, Martin Weinmann

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

Comments accepted to ISPRS Journal

2112.08879 2022-07-22 cs.CV cs.CL 79%

Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds

Ayush Jain, Nikolaos Gkanatsios, Ishita Mediratta, Katerina Fragkiadaki

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

Comments First two authors contributed equally | ECCV 2022 Camera Ready

2111.11187 2022-07-21 cs.CV 79%

PointMixer: MLP-Mixer for Point Cloud Understanding

Jaesung Choe, Chunghyun Park, Francois Rameau, Jaesik Park, In So Kweon

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

Comments Accepted to ECCV 2022

2207.09084 2022-07-20 cs.CV 79%

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Zhonghua Wu, Yicheng Wu, Guosheng Lin, Jianfei Cai, Chen Qian

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

Comments ECCV 2022

2203.03833 2022-07-20 cs.CV cs.AI 79%

Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap

Yongwei Chen, Zihao Wang, Longkun Zou, Ke Chen, Kui Jia

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

Comments Accepted by ECCV 2022

1. 点云 7732 篇

PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees

Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer

Real-time Rail Recognition Based on 3D Point Clouds

Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matching

3D Vision with Transformers: A Survey

Global Hierarchical Attention for 3D Point Cloud Analysis

Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter

IT/IST/IPLeiria Response to the Call for Proposals on JPEG Pleno Point Cloud Coding

IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compression

SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud

CloudAttention: Efficient Multi-Scale Attention Scheme For 3D Point Cloud Learning

PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds

Masked Discrimination for Self-Supervised Learning on Point Clouds

MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud

Explaining Deep Neural Networks for Point Clouds using Gradient-based Visualisations

3D Siamese Transformer Network for Single Object Tracking on Point Clouds

Accurate Ground-Truth Depth Image Generation via Overfit Training of Point Cloud Registration using Local Frame Sets

Dynamic 3D Scene Analysis by Point Cloud Accumulation

Salient Object Detection for Point Clouds

PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows

You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors

Lidar Point Cloud Guided Monocular 3D Object Detection

GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation

Few-shot Class-incremental Learning for 3D Point Cloud Objects

SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer

Beyond single receptive field: A receptive field fusion-and-stratification network for airborne laser scanning point cloud classification

Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds

PointMixer: MLP-Mixer for Point Cloud Understanding

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap