4 papers
FFHQ-Makeup: Paired Synthetic Makeup Dataset with Facial Consistency Across Multiple Styles
Xingchao Yang, Shiori Ueda, Yuantian Huang +2
Paired bare-makeup facial images are essential for a wide range of beauty-related tasks, such as virtual try-on, facial privacy protection, and facial aesthetics analysis. However,…
FreeUV: Ground-Truth-Free Realistic Facial UV Texture Recovery via Cross-Assembly Inference Strategy
Xingchao Yang, Takafumi Taketomi, Yuki Endo +1
Recovering high-quality 3D facial textures from single-view 2D images is a challenging task, especially under constraints of limited data and complex facial details such as makeup,…
BeautyBank: Encoding Facial Makeup in Latent Space
Qianwen Lu, Xingchao Yang, Takafumi Taketomi
The advancement of makeup transfer, editing, and image encoding has demonstrated their effectiveness and superior quality. However, existing makeup works primarily focus on low-dim…
TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolation
Haiyang Liu, Xingchao Yang, Tomoya Akiyama +4
We present TANGO, a framework for generating co-speech body-gesture videos. Given a few-minute, single-speaker reference video and target speech audio, TANGO produces high-fidelity…