Physically-Based Face Rendering for NIR-VIS Face Recognition

TL;DR

This paper introduces a physically-based rendering method to generate high-quality paired NIR-VIS face images, improving cross-modality face recognition by reducing domain gaps and focusing on identity features, without relying on existing datasets.

Contribution

The authors propose a novel 3D face reconstruction and reflectance transformation technique combined with a new loss function to generate realistic NIR-VIS face pairs and enhance recognition performance.

Findings

Achieves comparable results to state-of-the-art methods without existing datasets.

Significantly surpasses SOTA with fine-tuning on target datasets.

Provides high-resolution, photorealistic NIR-VIS face image datasets.

Abstract

Near infrared (NIR) to Visible (VIS) face matching is challenging due to the significant domain gaps as well as a lack of sufficient data for cross-modality model training. To overcome this problem, we propose a novel method for paired NIR-VIS facial image generation. Specifically, we reconstruct 3D face shape and reflectance from a large 2D facial dataset and introduce a novel method of transforming the VIS reflectance to NIR reflectance. We then use a physically-based renderer to generate a vast, high-resolution and photorealistic dataset consisting of various poses and identities in the NIR and VIS spectra. Moreover, to facilitate the identity feature learning, we propose an IDentity-based Maximum Mean Discrepancy (ID-MMD) loss, which not only reduces the modality gap between NIR and VIS images at the domain level but encourages the network to focus on the identity features instead of facial details, such as poses and accessories. Extensive experiments conducted on four challenging NIR-VIS face recognition benchmarks demonstrate that the proposed method can achieve comparable performance with the state-of-the-art (SOTA) methods without requiring any existing NIR-VIS face recognition datasets. With slightly fine-tuning on the target NIR-VIS face recognition datasets, our method can significantly surpass the SOTA performance. Code and pretrained models are released under the insightface (https://github.com/deepinsight/insightface/tree/master/recognition).