Shypd.aiThe largest open index of AI toolsSelfExSR is an open-source image super-resolution tool that enhances image quality by learning from transformed versions of the image itself. It achieves state-of-the-art performance without external training data.
Trending
Also listed in
About
SelfExSR is a research code implementation for single image super-resolution, based on the paper "Single Image Super-Resolution from Transformed Self-Exemplars" (CVPR 2015). This algorithm stands out by achieving state-of-the-art performance in image super-resolution without requiring any external training dataset, complex feature extraction, or complicated learning algorithms. It operates by learning from transformed self-exemplars within the image itself. The repository provides the MATLAB source code, testing images for various datasets (Set5, Set14, Urban 100, BSD 100, Sun-Hays 80), and precomputed results for comparison with other state-of-the-art methods. While designed as educational code and not optimized for speed, users can adjust iteration numbers for a trade-off between speed and visual quality.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
