Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion

Abstract

Chamfer Distance (CD) and Earth Mover's Distance (EMD) are two broadly adopted metrics for measuring the similarity between two point sets. However, CD is usually insensitive to mismatched local density, and EMD is usually dominated by global distribution while overlooks the fidelity of detailed structures. Besides, their unbounded value range induces a heavy influence from the outliers. These defects prevent them from providing a consistent evaluation. To tackle these problems, we propose a new similarity measure named Density-aware Chamfer Distance (DCD). It is derived from CD and benefits from several desirable properties: 1) it can detect disparity of density distributions and is thus a more intensive measure of similarity compared to CD; 2) it is stricter with detailed structures and significantly more computationally efficient than EMD; 3) the bounded value range encourages a more stable and reasonable evaluation over the whole test set. We adopt DCD to evaluate the point cloud completion task, where experimental results show that DCD pays attention to both the overall structure and local geometric details and provides a more reliable evaluation even when CD and EMD contradict each other. We can also use DCD as the training loss, which outperforms the same model trained with CD loss on all three metrics. In addition, we propose a novel point discriminator module that estimates the priority for another guided down-sampling step, and it achieves noticeable improvements under DCD together with competitive results for both CD and EMD. We hope our work could pave the way for a more comprehensive and practical point cloud similarity evaluation. Our code will be available at: https://github.com/wutong16/Density_aware_Chamfer_Distance .

Accepted to NeurIPS 2021

Cited by in corpus (9)

• Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis
• High Resolution Point Clouds from mmWave Radar
• Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery
• Shape Completion with Points in the Shadow
• SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization
• Irregular Change Detection in Sparse Bi-Temporal Point Clouds using Learned Place Recognition Descriptors and Point-to-Voxel Comparison
• Denoising-While-Completing Network (DWCNet): Robust Point Cloud Completion Under Corruption
• Neural Garment Dynamics via Manifold-Aware Transformers
• BRep Boundary and Junction Detection for CAD Reverse Engineering