论文标题
重新思考图像超分辨率的数据增强：全面分析和新策略
Rethinking Data Augmentation for Image Super-resolution: A Comprehensive Analysis and a New Strategy
论文作者
论文摘要
数据增强是提高深网性能的有效方法。不幸的是，当前的方法主要是针对高级视觉任务（例如，分类）开发的，很少有人研究用于低级视觉任务（例如，图像恢复）。在本文中，我们对应用于超分辨率任务的现有增强方法进行了全面分析。我们发现，丢弃或操纵像素的方法或特征太多阻碍了图像恢复，而空间关系非常重要。根据我们的分析，我们提出了切割低分辨率贴片并将其粘贴到相应的高分辨率图像区域的Cutblur，反之亦然。 Cutblur的关键直觉是使模型不仅能够学习“如何”，还可以学习“在哪里”以超级溶解图像。通过这样做，该模型可以理解“多少”，而不是盲目学习将超分辨率应用于每个给定的像素。我们的方法始终如一地显着改善了各种情况的性能，尤其是当模型大小很大并且数据在现实世界环境下收集时。我们还表明，我们的方法改善了其他低级视力任务，例如去核和压缩伪像去除。
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.
