Training Patch Analysis and Mining Skills for Image Restoration Deep Neural Networks
This work addresses a practical problem for researchers and practitioners in computer vision by providing incremental improvements in training data preparation for image restoration.
The paper tackles the lack of detailed training methods in image restoration deep neural networks by analyzing training patches and proposing a guideline for patch extraction from given images, aiming to improve reproducibility and reduce the need for costly new datasets.
There have been numerous image restoration methods based on deep convolutional neural networks (CNNs). However, most of the literature on this topic focused on the network architecture and loss functions, while less detailed on the training methods. Hence, some of the works are not easily reproducible because it is required to know the hidden training skills to obtain the same results. To be specific with the training dataset, few works discussed how to prepare and order the training image patches. Moreover, it requires a high cost to capture new datasets to train a restoration network for the real-world scene. Hence, we believe it is necessary to study the preparation and selection of training data. In this regard, we present an analysis of the training patches and explore the consequences of different patch extraction methods. Eventually, we propose a guideline for the patch extraction from given training images.