CutBlur

2000년 도입 · 논문 1편에서 사용

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.

출처: Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy

소개 논문: Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy