Institute of Technology, 2Chinese Academy
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
J. B. Shen, X.S. Yang, Y.D. Jia, X.L. Li. Intrinsic Images Using Optimization.
IEEE CVPR, pp. 3481-3487,
J. B. Shen, X. S. Yang, X. L. Li, Y. D. Jia.
Intrinsic images decomposition using optimization and user scribbles.
IEEE Transactions on Cybernetics, 43(2):425-436, 2013
If you are using our code in your publication,
please cite our papers, Thanks.
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.