IEEE Signal Processing Letters · 2015 · 46 citations · 27 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDeep LearningDimensionality ReductionImage Feature EngineeringRepresentation LearningImage Super-resolutionJoint Representation LearningLocal RegressionMixture Of Experts FusionNetwork-based LearningSuper-resolutionSuper-resolution Image Analysis
Using a global regression model for single image super-resolution (SISR) generally fails to produce visually pleasant output. The recently developed local learning methods provide a remedy by partitioning the feature space into a number of clusters and learning a simple local model for each cluster. However, in these methods the space partition is conducted separately from local model learning, which results in an abundant number of local models to achieve satisfying performance. To address this problem, we propose a mixture of experts (MoE) method to jointly learn the feature space partition and local regression models. Our MoE consists of two components: gating network learning and local regressors learning. An expectation-maximization (EM) algorithm is adopted to train MoE on a large set of LR/HR patch pairs. Experimental results demonstrate that the proposed method can use much less local models and time to achieve comparable or superior results to state-of-the-art SISR methods, providing a highly practical solution to real applications.
27
Image quality assessment: from error visibility to structural similarity
Zhou Wang, Alan C. Bovik, Hamid R. Sheikh et al. · IEEE Transactions on Image Processing · 2004 · 56K citations
Nonlinear Dimensionality Reduction by Locally Linear Embedding
Sam T. Roweis, Lawrence K. Saul · Science · 2000 · 15K citations
Image Super-Resolution Via Sparse Representation
John Wright, Thomas S. Huang, Yi Ma · IEEE Transactions on Image Processing · 2010 · 5.3K citations
Adaptive Mixtures of Local Experts
Robert A. Jacobs, Michael I. Jordan, Steven J. Nowlan et al. · Neural Computation · 1991 · 5K citations