Journal article 385 views 174 downloads
Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption
,
Lyndon Hill,
Mark Jones ,
Gary Tam
Computers & Graphics, Volume: 132, Start page: 104401
Swansea University Authors:
Keneni Tesema , Mark Jones , Gary Tam
-
PDF | Version of Record
© 2025 The Authors. This is an open access article distributed under the terms of the Creative Commons CC-BY license.
Download (10.01MB)
DOI (Published version): 10.1016/j.cag.2025.104401
Abstract
Point cloud completion is crucial for 3D computer vision tasks in autonomous driving, augmented reality, and robotics. However, obtaining clean and complete point clouds from real-world environments is challenging due to noise and occlusions. Consequently, most existing completion networks – trained...
| Published in: | Computers & Graphics |
|---|---|
| ISSN: | 0097-8493 1873-768 |
| Published: |
Elsevier BV
2025
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa69951 |
| Abstract: |
Point cloud completion is crucial for 3D computer vision tasks in autonomous driving, augmented reality, and robotics. However, obtaining clean and complete point clouds from real-world environments is challenging due to noise and occlusions. Consequently, most existing completion networks – trained on synthetic data – struggle with real-world degradations. In this work, we tackle the problem of completing and denoising highly corrupted partial point clouds affected by multiple simultaneous degradations. To benchmark robustness, we introduce the Corrupted Point Cloud Completion Dataset (CPCCD), which highlights the limitations of current methods under diverse corruptions. Building on these insights, we propose DWCNet (Denoising-While-Completing Network), a completion framework enhanced with a Noise Management Module (NMM) that leverages contrastive learning and self-attention to suppress noise and model structural relationships. DWCNet achieves state-of-the-art performance on both clean and corrupted, synthetic and real-world datasets. The dataset and code will be publicly available at https://github.com/keneniwt/DWCNET-Robust-Point-Cloud-Completion-against-Corruptions. |
|---|---|
| Keywords: |
Point cloud completion; Point cloud denoising; Robustness benchmark dataset |
| College: |
Faculty of Science and Engineering |
| Funders: |
This work was funded by EPSRC, United Kingdom grant number EP/S021892/1 and Beam (Previously Vaarst) (beam.global). Tam is partially supported by a Royal Society, United Kingdom fund IEC/NSFC/211159. |
| Start Page: |
104401 |