On-Demand Learning for Deep Image Restoration

While machine learning approaches to image restoration offer great promise, current methods risk training models fixated on performing well only for image corruption of a particular level of difficultysuch as a certain level of noise or blur. First, we examine the weakness of conventional "fixated" models and demonstrate that training general models to handle arbitrary levels of corruption is indeed non-trivial. Then, we propose an on-demand learning algorithm for training image restoration models with deep convolutional neural networks. The main idea is to exploit a feedback mechanism to self-generate training instances where they are needed most, thereby learning models that can generalize across difficulty levels. On four restoration tasksimage inpainting, pixel interpolation, image deblurring, and image denoisingand three diverse datasets, our approach consistently outperforms both the status quo training procedure and curriculum learning alternatives.