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

TL;DR

This paper introduces DWCNet, a robust point cloud completion network that effectively denoises and completes corrupted point clouds, addressing real-world challenges in 3D vision tasks with a new benchmark dataset.

Contribution

The paper presents DWCNet with a Noise Management Module utilizing contrastive learning and self-attention, and introduces the CPCCD dataset for benchmarking robustness against corruptions.

Findings

DWCNet outperforms existing methods on both synthetic and real-world corrupted datasets.

The CPCCD dataset reveals limitations of current methods under diverse corruptions.

DWCNet achieves state-of-the-art results in denoising and completing corrupted point clouds.

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