March 20, 2024, 4:45 a.m. | Yunqi Miao, Jiankang Deng, Jungong Han

cs.CV updates on arXiv.org arxiv.org

arXiv:2403.12760v1 Announce Type: new
Abstract: Although diffusion models are rising as a powerful solution for blind face restoration, they are criticized for two problems: 1) slow training and inference speed, and 2) failure in preserving identity and recovering fine-grained facial details. In this work, we propose WaveFace to solve the problems in the frequency domain, where low- and high-frequency components decomposed by wavelet transformation are considered individually to maximize authenticity as well as efficiency. The diffusion model is applied to …

abstract arxiv authentic blind cs.cv diffusion diffusion models face failure fine-grained identity inference recovery solution solve speed training type work

Lead Developer (AI)

@ Cere Network | San Francisco, US

Research Engineer

@ Allora Labs | Remote

Ecosystem Manager

@ Allora Labs | Remote

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote