Self-supervised Learning For Point Clouds
Self-Supervised Learning for Point Clouds is a machine learning paradigm that enables the extraction of meaningful representations from unlabeled three-dimensional point cloud data by leveraging intrinsic geometric or structural priors to define pretext tasks that guide feature learning without human-annotated labels.
154
Publications
7.2K
Citations
520
Authors
156
Institutions
Publications per year
2017–2026
154
Parents
154
D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
Xuyang Bai, Zixin Luo, Lei Zhou et al. · 2020 · 495 citations
ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
Jihan Yang, Shaoshuai Shi, Zhe Wang et al. · 2021 · 187 citations
1–5 of 154
520
5
h-index
5
h-index
5
h-index
4
h-index
4
h-index
1–5 of 520
156
Tsinghua University
Beijing, China
11 h-index
20 publications
1.3K citations

Shanghai Jiao Tong University
Shanghai, China
9 h-index
16 publications
616 citations

Peking University
Beijing, China
9 h-index
17 publications
1.3K citations
Chinese University of Hong Kong
Hong Kong, Hong Kong
8 h-index
16 publications
1.2K citations

University of Hong Kong
Pok Fu Lam, Hong Kong
7 h-index
8 publications
861 citations
University of Bonn
Bonn, Germany
6 h-index
24 publications
845 citations
Carnegie Mellon University
Pittsburgh, United States
5 h-index
12 publications
554 citations
Peng Cheng Laboratory
Shenzhen, China
5 h-index
10 publications
512 citations
1–8 of 156
Repository · 24 publications · 811 citations
14
h-index
Conference · 9 publications · 746 citations
9
h-index
Conference · 8 publications · 898 citations
8
h-index
6 publications · 199 citations
7
h-index
Conference · 4 publications · 238 citations
5
h-index
1–5