Deep Bi-Dense Networks for Image Super-Resolution

TL;DR

This paper introduces Deep Bi-Dense Networks (DBDN) for single image super-resolution, utilizing novel inter- and intra-block dense connections to enhance feature propagation and improve performance over existing methods.

Contribution

The paper proposes a new deep bi-dense network architecture with inter- and intra-block dense connections for superior image super-resolution.

Findings

Outperforms state-of-the-art methods on five benchmark datasets.

Achieves higher PSNR and SSIM scores with moderate network parameters.

Effectively alleviates vanishing gradient problems during training.

Abstract

This paper proposes Deep Bi-Dense Networks (DBDN) for single image super-resolution. Our approach extends previous intra-block dense connection approaches by including novel inter-block dense connections. In this way, feature information propagates from a single dense block to all subsequent blocks, instead of to a single successor. To build a DBDN, we firstly construct intra-dense blocks, which extract and compress abundant local features via densely connected convolutional layers and compression layers for further feature learning. Then, we use an inter-block dense net to connect intra-dense blocks, which allow each intra-dense block propagates its own local features to all successors. Additionally, our bi-dense construction connects each block to the output, alleviating the vanishing gradient problems in training. The evaluation of our proposed method on five benchmark datasets shows that our DBDN outperforms the state of the art in SISR with a moderate number of network parameters.