S3Editor: A Sparse Semantic-Disentangled Self-Training Framework for Face Video Editing

arXiv:2404.08111v1 Announce Type: new
Abstract: Face attribute editing plays a pivotal role in various applications. However, existing methods encounter challenges in achieving high-quality results while preserving identity, editing faithfulness, and temporal consistency. These challenges are rooted in issues related to the training pipeline, including limited supervision, architecture design, and optimization strategy. In this work, we introduce S3Editor, a Sparse Semantic-disentangled Self-training framework for face video editing. S3Editor is a generic solution that comprehensively addresses these challenges with three key contributions. …

abstract applications architecture arxiv challenges cs.ai cs.cl cs.cv design editing face framework however identity optimization pipeline pivotal quality results role self-training semantic supervision temporal training training pipeline type video