A Robust Class-based Reflectance Rendering for Face Images

It is very difficult to recover the illumination-invariant reflectance from a single input image because it is an ill conditioned problem. In this paper structure similarity between the reflectance image and its illuminated image is revealed firstly based on an ideal class definition. Then a simple linear reconstruction scheme is successfully proposed for reflectance rendering, in which the reflectance face images are learnt (or generated) from the training examples in terms of this structure similarity. Principal Component Analysis and Robust Estimation are adopted to get a robust rendering result. Extensive experiments show that the proposed method is efficacious in separating reflectance from an input face image, and reducing the variation caused by lighting conditions. Furthermore, this method can be used directly to render new images of the input face under different lighting conditions.