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