Abstract
Previous feed-forward architectures of recently proposed deep super-resolution networks learn the features of low-resolution inputs and the non-linear mapping from those to a high-resolution output. However, this approach does not fully address the mutual dependencies of low- and high-resolution images. We propose Deep Back-Projection Networks (DBPN), the winner of two image super-resolution challenges (NTIRE2018 and PIRM2018), that exploit iterative up- and down-sampling layers. These layers are formed as a unit providing an error feedback mechanism for projection errors. We construct mutually-connected up- and down-sampling units each of which represents different types of low- and high-resolution components. We also show that extending this idea to demonstrate a new insight towards more efficient network design substantially, such as parameter sharing on the projection module and transition layer on projection step. The experimental results yield superior results and in particular establishing new state-of-the-art results across multiple data sets, especially for large scaling factors such as 8×.
Highlights
We found these settings to work well based on general intuition and preliminary experiments
We can see that increasing nR can improve the performance of Deep Back-Projection Networks (DBPN)-R which is shown by DBPN-R128-5 compare to DBPN-R64-10
We have proposed Deep Back-Projection Networks for Single Image Super-resolution which is the winner of two single image SR challenge (NTIRE2018 and PIRM2018)
Summary
S IGNIFICANT progress in deep neural network (DNN) for vision [1], [2], [3], [4], [5], [6], [7] has recently been propagating to the field of super-resolution (SR) [8], [9], [10], [11], [12], [13], [14], [15], [16].Single image SR (SISR) is an ill-posed inverse problem where the aim is to recover a high-resolution (HR) image from a low-resolution (LR) image. For DNN approach, the networks compute a sequence of feature maps from the LR image, culminating with one or more upsampling layers to increase resolution and construct the HR image. In contrast to this purely feed-forward approach, the human visual system is believed to use a feedback connection to guide the task for the relevant results [25], [26], [27]. Perhaps hampered by lack of such feedback, the current SR networks with only feed-forward connections have difficulty in representing the LR-to-HR relation, especially for large scaling factors
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Transactions on Pattern Analysis and Machine Intelligence
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.