Intrinsic Images Using Optimization

Jianbing Shen1, Xiaoshan Yang1, Yunde Jia1, Xuelong Li2

1Beijing Institute of Technology, 2Chinese Academy of Sciences


In this paper, we present a novel high-quality intrinsic image recovery approach using optimization. Our approach is based on the assumption of color characteristics in a local window in natural images. Our method adopts a premise that neighboring pixels in a local window of a single image having similar intensity values should have similar reflectance values. Thus the intrinsic image decomposition is formulated by optimizing an energy function with adding a weighting constraint to the local image properties. In order to improve the intrinsic image extraction results, we specify local constrain cues by integrating the user strokes in our energy formulation, including constant-reflectance, constant-illumination and fixed-illumination brush. Our experimental results demonstrate that our approach achieves a better recovery of intrinsic reflectance and illumination components than by previous approaches.




This work was supported by the National Natural Science Foundation of China (Grant Nos. 60903068 and 61072093), the Key Program of NSFC-Guangdong Union Foundation (Grant No. U1035004) and the Excellent Young Teacher Research Fund of Beijing Institute of Technology (2009Y0707). The Project-sponsored by SRF for ROCS, SEM.


Send any comments or questions to Jianbing Shen (Email : or )