Confidence-Aware RGB-D Face Recognition via Virtual Depth Synthesis

arXiv:2403.06529v1 Announce Type: new
Abstract: 2D face recognition encounters challenges in unconstrained environments due to varying illumination, occlusion, and pose. Recent studies focus on RGB-D face recognition to improve robustness by incorporating depth information. However, collecting sufficient paired RGB-D training data is expensive and time-consuming, hindering wide deployment. In this work, we first construct a diverse depth dataset generated by 3D Morphable Models for depth model pre-training. Then, we propose a domain-independent pre-training framework that utilizes readily available pre-trained RGB …

abstract arxiv challenges confidence cs.cv data deployment environments face face recognition focus however information recognition rgb-d robustness studies synthesis training training data type via virtual work