Deep Bi-Dense Networks for Image Super-Resolution
This work addresses image super-resolution for computer vision applications, presenting an incremental improvement over existing dense connection methods.
The paper tackles single image super-resolution by proposing Deep Bi-Dense Networks (DBDN), which introduce inter-block dense connections to propagate features across all subsequent blocks, and it outperforms state-of-the-art methods on five benchmark datasets with a moderate number of parameters.
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.