Gradient-Domain Image Reconstruction Framework with Intensity-Range and Base-Structure Constraints

Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi



This paper presents a novel unified gradient-domain image reconstruction framework with intensity-range con- straint and base-structure constraint. The existing method for manipulating base structures and detailed textures are classifiable into two major approaches: i) gradient-domain and ii) layer-decomposition. To generate detail-preserving and artifact-free output images, we combine the benefits of the two approaches into the proposed framework by intro- ducing the intensity-range constraint and the base-structure constraint. To preserve details of the input image, the pro- posed method takes advantage of reconstructing the out- put image in the gradient domain, while the output inten- sity is guaranteed to lie within the specified intensity range, e.g. 0-to-255, by the intensity-range constraint. In addition, the reconstructed image lies close to the base structure by the base-structure constraint, which is effective for restrain- ing artifacts. Experimental results show that the proposed framework is effective for various applications such as tone mapping, seamless image cloning, detail enhancement, and image restoration.




Supplemental Movie



Publication

Gradient-Domain Image Reconstruction Framework with Intensity-Range and Base-Structure Constraints
Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 [ PDF] [ code]