.png){kind=icon}
.png){kind=icon}
Return
Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption
.png){kind=icon}
PRE
AI
DOI：10.1016/j.cag.2025.104401.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We formulate and systematically approach an existing but underexplored problem in point cloud completion: the challenge of completing highly corrupted (noisy) partial point clouds. • We introduce a novel corrupted point cloud completion dataset (CPCCD) as the first robustness benchmark in the field of point cloud completion. • We offer the first systematic evaluation of the robustness of completion networks, examining how robustness relates to different types of corruptions and network architectures. • We introduce DWCNet, a completion algorithm that integrates denoising and completion through a novel Noise Management Module, producing relatively clean, complete point clouds from noisy inputs. DWCNet achieves state-of-the-art results on the PCN, CPCCD, and ScanObjectNN datasets, demonstrating robustness on corrupted data.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.