Contrastive Learning for 3D Point Clouds Classification and Shape Completion
In this paper, we present the idea of Self Supervised learning on the shape completion and classification of point clouds. Most 3D shape completion pipelines utilize AutoEncoders to extract features from point clouds used in downstream tasks such as classification, segmentation, detection, and other...
Main Authors: | Danish Nazir, Muhammad Zeshan Afzal, Alain Pagani, Marcus Liwicki, Didier Stricker |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/21/7392 |
Similar Items
-
Multistage Adaptive Point-Growth Network for Dense Point Cloud Completion
by: Ruidong Hao, et al.
Published: (2022-10-01) -
Colored Point Cloud Completion for a Head Using Adversarial Rendered Image Loss
by: Yuki Ishida, et al.
Published: (2022-04-01) -
3D-PCGR: Colored Point Cloud Generation and Reconstruction with Surface and Scale Constraints
by: Chaofeng Yuan, et al.
Published: (2024-03-01) -
View-Agnostic Point Cloud Generation for Occlusion Reduction in Aerial Lidar
by: Nina Singer, et al.
Published: (2022-06-01) -
Cyclic Global Guiding Network for Point Cloud Completion
by: Ming Wei, et al.
Published: (2022-07-01)