Single-Shot Facial Appearance Acquisition without Statistical Appearance Priors

Single-shot in-the-wild facial reflectance acquisition has been a long-standing challenge in the field of computer graphics and computer vision. Current state-of-the-art methods are typically learning-based methods, pre-trained on a dataset of facial reflectance data. However, due to the high cost and time-consuming nature of gathering these datasets, they are usually limited in the number of subjects covered and hence are prone to biases in the dataset. To this end, we propose a novel multi-stage guided optimization with differentiable rendering to tackle this problem, without the use of statistical facial appearance priors. This makes our method immune to these biases, and we demonstrate the advantage with qualitative and quantitative evaluations against current state-of-the-art methods.