FaceXFormer: A Unified Transformer for Facial Analysis

arXiv:2403.12960v1 Announce Type: new
Abstract: In this work, we introduce FaceXformer, an end-to-end unified transformer model for a comprehensive range of facial analysis tasks such as face parsing, landmark detection, head pose estimation, attributes recognition, and estimation of age, gender, race, and landmarks visibility. Conventional methods in face analysis have often relied on task-specific designs and preprocessing techniques, which limit their approach to a unified architecture. Unlike these conventional methods, our FaceXformer leverages a transformer-based encoder-decoder architecture where each task …

abstract age analysis arxiv cs.cv detection face facial analysis gender head landmark parsing race recognition tasks transformer transformer model type visibility work