A Fine Rendering High-Resolution Makeup Transfer network via inversion-editing strategy

Zhaoyang Sun, Shengwu Xiong, Yaxiong Chen, Yi Rong

Abstract: Highlights•We propose a novel Fine Rendering High-resolution Makeup Transfer (FRHMT) method.•We design the Hierarchical Residual Inversion module to preserve the image contents.•Our proposed training process eliminates the need for pseudo-paired data synthesis.•A new dataset consisting of 9,716 high-resolution facial images is collected.