TY - GEN
T1 - Semi-coupled dictionary learning with applications to image super-resolution and photo-sketch synthesis
AU - Wang, Shenlong
AU - Zhang, Lei
AU - Liang, Yan
AU - Pan, Quan
PY - 2012
Y1 - 2012
N2 - In various computer vision applications, often we need to convert an image in one style into another style for better visualization, interpretation and recognition; for examples, up-convert a low resolution image to a high resolution one, and convert a face sketch into a photo for matching, etc. A semi-coupled dictionary learning (SCDL) model is proposed in this paper to solve such cross-style image synthesis problems. Under SCDL, a pair of dictionaries and a mapping function will be simultaneously learned. The dictionary pair can well characterize the structural domains of the two styles of images, while the mapping function can reveal the intrinsic relationship between the two styles' domains. In SCDL, the two dictionaries will not be fully coupled, and hence much flexibility can be given to the mapping function for an accurate conversion across styles. Moreover, clustering and image nonlocal redundancy are introduced to enhance the robustness of SCDL. The proposed SCDL model is applied to image super-resolution and photo-sketch synthesis, and the experimental results validated its generality and effectiveness in cross-style image synthesis.
AB - In various computer vision applications, often we need to convert an image in one style into another style for better visualization, interpretation and recognition; for examples, up-convert a low resolution image to a high resolution one, and convert a face sketch into a photo for matching, etc. A semi-coupled dictionary learning (SCDL) model is proposed in this paper to solve such cross-style image synthesis problems. Under SCDL, a pair of dictionaries and a mapping function will be simultaneously learned. The dictionary pair can well characterize the structural domains of the two styles of images, while the mapping function can reveal the intrinsic relationship between the two styles' domains. In SCDL, the two dictionaries will not be fully coupled, and hence much flexibility can be given to the mapping function for an accurate conversion across styles. Moreover, clustering and image nonlocal redundancy are introduced to enhance the robustness of SCDL. The proposed SCDL model is applied to image super-resolution and photo-sketch synthesis, and the experimental results validated its generality and effectiveness in cross-style image synthesis.
UR - http://www.scopus.com/inward/record.url?scp=84866652383&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84866652383&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2012.6247930
DO - 10.1109/CVPR.2012.6247930
M3 - Conference contribution
AN - SCOPUS:84866652383
SN - 9781467312264
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2216
EP - 2223
BT - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
T2 - 2012 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2012
Y2 - 16 June 2012 through 21 June 2012
ER -