CVPR2023

Improving Fairness in Facial Albedo Estimation via Visual-Textual Cues

Xingyu Ren, Jiankang Deng, Chao Ma, Yichao Yan, Xiaokang Yang

摘要

Figure 1 . We introduce ID2Albedo, a high-quality, unbiased albedo reconstruction method. ID2Albedo maps the facial identity features to the latent space of the albedo generator and uses novel visual-textual cues to constrain albedo attributes. Our approach can alleviate the illumination/albedo ambiguity and generate high-fidelity albedo maps for realistic rendering. Images are all from FFHQ [30] dataset.