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

2025-07-22

AI Summary

Addressing the challenging problem of completing highly degraded partial point clouds under realistic scenarios where multiple noise types coexist with occlusions, this paper proposes DWCNet—a novel end-to-end deep network framework that jointly performs structural reconstruction and noise suppression for the first time. Its core innovation is the Noise Management Module (NMM), which integrates contrastive learning with self-attention to explicitly model geometric structural relationships and robustly suppress complex noise. To systematically evaluate performance under multi-degradation conditions, we introduce CPCCD—the first benchmark dataset specifically designed for point cloud completion under compound corruptions. Extensive experiments demonstrate that DWCNet achieves state-of-the-art performance across clean/degraded and synthetic/real-world point cloud benchmarks, exhibiting strong generalization capability. It significantly enhances the robustness and practicality of point cloud processing in real-world 3D vision applications, including autonomous driving and augmented reality.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Safety and Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Web Mining and Content Analysis: Web data integration and cleaning

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

Problem

• Completing noisy partial point clouds
• Handling multiple simultaneous degradations
• Improving robustness in real-world conditions

Innovation

• Denoising-While-Completing Network (DWCNet)
• Noise Management Module (NMM)
• Contrastive learning and self-attention