2004 · 2K citations · 22 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningRepresentation LearningScene ReconstructionHigh-resolution ImagingImage Super-resolutionLocally Linear EmbeddingManifold LearningSuper-resolutionSuper-resolution ImagingSuper-resolution ProcessingSuper-resolution Reconstruction
In this paper, we propose a novel method for solving single-image super-resolution problems. Given a low-resolution image as input, we recover its high-resolution counterpart using a set of training examples. While this formulation resembles other learning-based methods for super-resolution, our method has been inspired by recent manifold teaming methods, particularly locally linear embedding (LLE). Specifically, small image patches in the lowand high-resolution images form manifolds with similar local geometry in two distinct feature spaces. As in LLE, local geometry is characterized by how a feature vector corresponding to a patch can be reconstructed by its neighbors in the feature space. Besides using the training image pairs to estimate the high-resolution embedding, we also enforce local compatibility and smoothness constraints between patches in the target high-resolution image through overlapping. Experiments show that our method is very flexible and gives good empirical results.
22
Nonlinear Dimensionality Reduction by Locally Linear Embedding
Sam T. Roweis, Lawrence K. Saul · Science · 2000 · 15K citations
A Global Geometric Framework for Nonlinear Dimensionality Reduction
Joshua B. Tenenbaum, Vin de Silva, John Langford · Science · 2000 · 13.7K citations
Marcelo Bertalmı́o, Guillermo Sapiro, V. Caselles et al. · 2000 · 3.6K citations · Full text