In this paper, the learning-based single image super-resolution (SR) is regarded as a problem of space structure learning. We propose a new SR method that identifies a space from the low-resolution (LR) image space that best preserves the structure of the high-resolution (HR) image space. The inference between the two structure-consistent spaces proves to be accurate and predicts HR image patches with higher quality. An effective iterative algorithm is also proposed to find the near-optimal solution to the model, which can be easily implemented in parallel computing. Extensive experiments are performed to show the effectiveness of the proposed algorithm.
- Metric learning
- Single image super-resolution
- Space structure learning
ASJC Scopus subject areas
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence