Image super-resolution using local learnable kernel regression

Authors:
Renjie Liao;Zengchang Qin
Affiliations:
Intelligent Computing and Machine Learning Lab, School of Automation Science and Electrical Engineering, Beihang University, Beijing, China;Intelligent Computing and Machine Learning Lab, School of Automation Science and Electrical Engineering, Beihang University, Beijing, China
Venue:
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Year:
2012

Citing 12
Cited 0

Approximate nearest neighbor queries in fixed dimensions

SODA '93 Proceedings of the fourth annual ACM-SIAM Symposium on Discrete algorithms
Learning Low-Level Vision

International Journal of Computer Vision - Special issue on statistical and computational theories of vision: modeling, learning, sampling and computing, Part I
Example-Based Super-Resolution

IEEE Computer Graphics and Applications
Limits on Super-Resolution and How to Break Them

IEEE Transactions on Pattern Analysis and Machine Intelligence
Fundamental Limits of Reconstruction-Based Superresolution Algorithms under Local Translation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Image upsampling via imposed edge statistics

ACM SIGGRAPH 2007 papers
Fast image/video upsampling

ACM SIGGRAPH Asia 2008 papers
Super-resolution without explicit subpixel motion estimation

IEEE Transactions on Image Processing
Image super-resolution via sparse representation

IEEE Transactions on Image Processing
Image and video upscaling from local self-examples

ACM Transactions on Graphics (TOG)
New edge-directed interpolation

IEEE Transactions on Image Processing
Image quality assessment: from error visibility to structural similarity

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we address the problem of learning-based image super-resolution and propose a novel approach called Local Learnable Kernel Regression (LLKR). The proposed model employs a local metric learning method to improve the kernel regression for reconstructing high resolution images. We formulate the learning problem as seeking multiple optimal Mahalanobis metrics to minimize the total kernel regression errors on the training images. Through learning local metrics in the space of low resolution image patches, our method is capable to build a precise data-adaptive kernel regression model in the space of high resolution patches. Since the local metrics split the whole data set into several subspaces and the training process can be executed off-line, our method is very efficient at runtime. We demonstrate that the new developed method is comparable or even outperforms other super-resolution algorithms on benchmark test images. The experimental results also show that our algorithm can still achieve a good performance even with a large magnification factor.