Toward Tiny and High-quality Facial Makeup with Data Amplify Learning

arXiv:2403.15033v1 Announce Type: new
Abstract: Contemporary makeup approaches primarily hinge on unpaired learning paradigms, yet they grapple with the challenges of inaccurate supervision (e.g., face misalignment) and sophisticated facial prompts (including face parsing, and landmark detection). These challenges prohibit low-cost deployment of facial makeup models, especially on mobile devices. To solve above problems, we propose a brand-new learning paradigm, termed "Data Amplify Learning (DAL)," alongside a compact makeup model named "TinyBeauty." The core idea of DAL lies in employing a …

abstract amplify arxiv challenges cost cs.cv data deployment detection devices face hinge landmark low mobile mobile devices parsing prompts quality supervision type