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 8x.

Deep Back-Projection Networks (DBPN) effectively address the mutual dependencies of low- and high-resolution images through iterative up- and down-sampling layers and mutual connections, achieving state-of-the-art results in image super-resolution with large scaling factors such as 8x.