CutBlur is a data augmentation method that is specifically designed for the low-level vision tasks. It cuts a low-resolution patch and pastes it to the corresponding high-resolution image region and vice versa. The key intuition of Cutblur is to enable a model to learn not only "how" but also "where" to super-resolve an image. By doing so, the model can understand "how much" instead of blindly learning to apply super-resolution to every given pixel.
Source: Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New StrategyPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Denoising | 1 | 25.00% |
Image Restoration | 1 | 25.00% |
Image Super-Resolution | 1 | 25.00% |
Super-Resolution | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |