Illumination transition image: Parameter-based illumination estimation and re-rendering

Jianyi Liu, Nanning Zheng, Lei Xiong, Gaofeng Meng, Shaoyi Du

Abstract: Varying illumination condition is a challenging problem for face recognition and synthesis. The illumination re-rendering technique allows aligning the illumination effects of facial images or relighting them as expected. In this paper, we propose an improved illumination re-rendering method based on more accurate mapping of facial images in the parametric illumination space. This will make the parameter-based illumination alignment more reliable. A clustering-based criterion is designed to evaluate its parameter estimation precision. To guide the image re-rendering between any a parameter pair, an intermediate image called the illumination transition image (ITI) is defined to represent both the illumination variation information and the person-specific facial shape features. The extensive experimental results verify the proposed method outperforms the quotient image approach on both parameter precision and rendering quality.