Data augmentation is an effective way to improve the performance of deep networks. Unfortunately, current methods are mostly developed for high-level vision tasks (e.g., classification) and few are studied for low-level vision tasks (e.g., image restoration). In this paper, we provide a comprehensive analysis of the existing augmentation methods applied to the super-resolution task. We find that the methods discarding or manipulating the pixels or features too much hamper the image restoration, where the spatial relationship is very important. Based on our analyses, we propose CutBlur that 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. Our method consistently and significantly improves the performance across various scenarios, especially when the model size is big and the data is collected under real-world environments. We also show that our method improves other low-level vision tasks, such as denoising and compression artifact removal.
We would like to thank Clova AI Research team, especially Yunjey Choi, Seong Joon Oh, Youngjung Uh, Sangdoo Yun, Dongyoon Han, Youngjoon Yoo, and Jung-Woo Ha for their valuable comments and feedback. This work was supported by NAVER Corp and also by the National Research Foundation of Korea grant funded by the Korea government (MSIT) (no.NRF-2019R1A2C1006608)