Face recognition on point cloud with cgan-top for denoising

TL;DR

This paper introduces an end-to-end 3D face recognition system that denoises noisy point clouds using a novel cGAN-TOP model and then recognizes faces with a hierarchical LDGCNN, significantly improving accuracy under noisy conditions.

Contribution

It presents a new integrated approach combining cGAN-TOP for denoising and LDGCNN for recognition, advancing 3D face recognition on noisy data.

Findings

Achieves up to 14.81% accuracy improvement under noise

Effectively denoises point clouds with cGAN-TOP

Enhances recognition robustness in noisy environments

Abstract

Face recognition using 3D point clouds is gaining growing interest, while raw point clouds often contain a significant amount of noise due to imperfect sensors. In this paper, an end-to-end 3D face recognition on a noisy point cloud is proposed, which synergistically integrates the denoising and recognition modules. Specifically, a Conditional Generative Adversarial Network on Three Orthogonal Planes (cGAN-TOP) is designed to effectively remove the noise in the point cloud, and recover the underlying features for subsequent recognition. A Linked Dynamic Graph Convolutional Neural Network (LDGCNN) is then adapted to recognize faces from the processed point cloud, which hierarchically links both the local point features and neighboring features of multiple scales. The proposed method is validated on the Bosphorus dataset. It significantly improves the recognition accuracy under all noise settings, with a maximum gain of 14.81%.