Improving 2D face recognition via fine-level facial depth generation and RGB-D complementary feature learning

TL;DR

This paper introduces a novel approach for 2D face recognition that leverages fine-level facial depth generation and enhanced RGB-D feature learning to improve accuracy in challenging scenarios.

Contribution

It proposes a fine-grained facial depth generation network and an improved multimodal feature learning network, addressing noise issues and enhancing feature extraction for RGB-D face recognition.

Findings

Achieves state-of-the-art accuracy on Lock3DFace and IIIT-D datasets.

Improves robustness of face recognition under pose, illumination, and occlusion variations.

Demonstrates effectiveness of proposed methods through extensive experiments.

Abstract

Face recognition in complex scenes suffers severe challenges coming from perturbations such as pose deformation, ill illumination, partial occlusion. Some methods utilize depth estimation to obtain depth corresponding to RGB to improve the accuracy of face recognition. However, the depth generated by them suffer from image blur, which introduces noise in subsequent RGB-D face recognition tasks. In addition, existing RGB-D face recognition methods are unable to fully extract complementary features. In this paper, we propose a fine-grained facial depth generation network and an improved multimodal complementary feature learning network. Extensive experiments on the Lock3DFace dataset and the IIIT-D dataset show that the proposed FFDGNet and I MCFLNet can improve the accuracy of RGB-D face recognition while achieving the state-of-the-art performance.