Proceedings of the 28th annual conference on Computer graphics and interactive techniques
On Advances in Statistical Modeling of Natural Images
Journal of Mathematical Imaging and Vision
Limits on Super-Resolution and How to Break Them
IEEE Transactions on Pattern Analysis and Machine Intelligence
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
MGMM: Multiresolution Gaussian Mixture Models for Computer Vision
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 1
Fundamental Limits of Reconstruction-Based Superresolution Algorithms under Local Translation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Blind Super-Resolution Using a Learning-Based Approach
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
An Improved Two-Step Approach to Hallucinating Faces
ICIG '04 Proceedings of the Third International Conference on Image and Graphics
Hallucinating Faces: TensorPatch Super-Resolution and Coupled Residue Compensation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
A hybrid MLP-PNN architecture for fast image superresolution
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
High-zoom video hallucination by exploiting spatio-temporal regularities
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Face hallucination with pose variation
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Direct energy minimization for super-resolution on nonlinear manifolds
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Superresolution video reconstruction with arbitrary sampling lattices and nonzero aperture time
IEEE Transactions on Image Processing
Joint MAP registration and high-resolution image estimation using a sequence of undersampled images
IEEE Transactions on Image Processing
IEEE Transactions on Image Processing
Resolution enhancement of color video sequences
IEEE Transactions on Image Processing
Eigenface-domain super-resolution for face recognition
IEEE Transactions on Image Processing
Super-resolution of images based on local correlations
IEEE Transactions on Neural Networks
IEEE Transactions on Image Processing
A Comprehensive Survey to Face Hallucination
International Journal of Computer Vision
| Hi-index | 0.00 |
Learning-based superresolution (SR) is a popular SR technique that uses application dependent priors to infer the missing details in low resolution images (LRIs). However, their performance still deteriorates quickly when the magnification factor is only moderately large. This leads us to an important problem: "Do limits of learning-based SR algorithms exist?" This paper is the first attempt to shed some light on this problem when the SR algorithms are designed for general natural images. We first define an expected risk for the SR algorithms that is based on the root mean squared error between the superresolved images and the ground truth images. Then utilizing the statistics of general natural images, we derive a closed form estimate of the lower bound of the expected risk. The lower bound only involves the covariance matrix and the mean vector of the high resolution images (HRIs) and hence can be computed by sampling real images. We also investigate the sufficient number of samples to guarantee an accurate estimate of the lower bound. By computing the curve of the lower bound w.r.t. the magnification factor, we could estimate the limits of learning-based SR algorithms, at which the lower bound of the expected risk exceeds a relatively large threshold. We perform experiments to validate our theory. And based on our observations we conjecture that the limits may be independent of the size of either the LRIs or the HRIs.