Facial UV Map Completion for Pose-invariant Face Recognition: A Novel Adversarial Approach based on Coupled Attention Residual UNets

TL;DR

This paper introduces a novel adversarial model with coupled attention residual UNets for completing UV maps of faces, enabling pose-invariant face recognition by synthesizing diverse facial images.

Contribution

The paper proposes a new generative model, Attention ResCUNet-GAN, that enhances UV map completion using coupled U-Nets with attention gates and feature fusion, improving pose-invariant face recognition.

Findings

Outperforms existing UV map completion methods on multiple benchmarks.

Improves pose-invariant face recognition accuracy.

Enhances synthetic face generation for training deep models.

Abstract

Pose-invariant face recognition refers to the problem of identifying or verifying a person by analyzing face images captured from different poses. This problem is challenging due to the large variation of pose, illumination and facial expression. A promising approach to deal with pose variation is to fulfill incomplete UV maps extracted from in-the-wild faces, then attach the completed UV map to a fitted 3D mesh and finally generate different 2D faces of arbitrary poses. The synthesized faces increase the pose variation for training deep face recognition models and reduce the pose discrepancy during the testing phase. In this paper, we propose a novel generative model called Attention ResCUNet-GAN to improve the UV map completion. We enhance the original UV-GAN by using a couple of U-Nets. Particularly, the skip connections within each U-Net are boosted by attention gates. Meanwhile, the features from two U-Nets are fused with trainable scalar weights. The experiments on the popular benchmarks, including Multi-PIE, LFW, CPLWF and CFP datasets, show that the proposed method yields superior performance compared to other existing methods.