Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption

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

Accepted for Computers and Graphics and EG Symposium on 3D Object Retrieval 2025 (3DOR'25)

References in corpus (14)

• ShapeNet: An Information-Rich 3D Model Repository
• Understanding Dimensional Collapse in Contrastive Self-supervised Learning
• Multi-Head Attention: Collaborate Instead of Concatenate
• Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion
• Intriguing Properties of Contrastive Losses
• P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds
• Benchmarking and Analyzing Point Cloud Classification under Corruptions
• Efficient Personalized Speech Enhancement through Self-Supervised Learning
• PointAttN: You Only Need Attention for Point Cloud Completion
• Temperature as Uncertainty in Contrastive Learning
• Multimodal Shape Completion via IMLE
• A Survey on Data Quality Dimensions and Tools for Machine Learning
• High-Fidelity Point Cloud Completion with Low-Resolution Recovery and Noise-Aware Upsampling
• RealDiff: Real-world 3D Shape Completion using Self-Supervised Diffusion Models