Sum-of-superellipses: a low parameter model for amplitude spectra of natural images
ICIAP'11 Proceedings of the 16th international conference on Image analysis and processing: Part I
Discriminant sparse neighborhood preserving embedding for face recognition
Pattern Recognition
Fast computation of edge model representation for image sequence super-resolution
PerMIn'12 Proceedings of the First Indo-Japan conference on Perception and Machine Intelligence
Greedy regression in sparse coding space for single-image super-resolution
Journal of Visual Communication and Image Representation
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Image upscaling using multiple dictionaries of natural image patches
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Image super resolution using Gaussian Process Regression with patch clustering
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Hi-index | 0.14 |
This paper proposes a framework for single-image super-resolution. The underlying idea is to learn a map from input low-resolution images to target high-resolution images based on example pairs of input and output images. Kernel ridge regression (KRR) is adopted for this purpose. To reduce the time complexity of training and testing for KRR, a sparse solution is found by combining the ideas of kernel matching pursuit and gradient descent. As a regularized solution, KRR leads to a better generalization than simply storing the examples as has been done in existing example-based algorithms and results in much less noisy images. However, this may introduce blurring and ringing artifacts around major edges as sharp changes are penalized severely. A prior model of a generic image class which takes into account the discontinuity property of images is adopted to resolve this problem. Comparison with existing algorithms shows the effectiveness of the proposed method.