Deep Back-Projection Networks For Super-Resolution
This work improves super-resolution for image processing applications, offering incremental advancements in network architecture.
The paper tackles the problem of super-resolution by addressing the mutual dependencies between low- and high-resolution images, proposing Deep Back-Projection Networks (DBPN) with iterative up- and down-sampling layers and error feedback, which achieves new state-of-the-art results for large scaling factors like 8x across multiple datasets.
The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to 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), that exploit iterative up- and down-sampling layers, providing an error feedback mechanism for projection errors at each stage. We construct mutually-connected up- and down-sampling stages each of which represents different types of image degradation and high-resolution components. We show that extending this idea to allow concatenation of features across up- and down-sampling stages (Dense DBPN) allows us to reconstruct further improve super-resolution, yielding superior results and in particular establishing new state of the art results for large scaling factors such as 8x across multiple data sets.