Denoising-While-Completing Network (DWCNet): Robust point cloud completion under corruption

摘要

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 . • 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.