Superior and Pragmatic Talking Face Generation with Teacher-Student Framework

arXiv:2403.17883v1 Announce Type: new
Abstract: Talking face generation technology creates talking videos from arbitrary appearance and motion signal, with the "arbitrary" offering ease of use but also introducing challenges in practical applications. Existing methods work well with standard inputs but suffer serious performance degradation with intricate real-world ones. Moreover, efficiency is also an important concern in deployment. To comprehensively address these issues, we introduce SuperFace, a teacher-student framework that balances quality, robustness, cost and editability. We first propose a simple …

abstract applications arxiv challenges cs.cv efficiency face framework inputs performance practical signal standard technology type videos work world