Hierarchical Back Projection Network for Image Super-Resolution
This work addresses image super-resolution for applications like photography and computer vision, presenting an incremental improvement over existing deep learning methods.
The authors tackled single image super-resolution by proposing a Hierarchical Back Projection Network (HBPN) that uses cascaded HourGlass modules and back projection blocks to capture spatial correlations and improve reconstruction, achieving state-of-the-art performance on various datasets including NTIRE2019.
Deep learning based single image super-resolution methods use a large number of training datasets and have recently achieved great quality progress both quantitatively and qualitatively. Most deep networks focus on nonlinear mapping from low-resolution inputs to high-resolution outputs via residual learning without exploring the feature abstraction and analysis. We propose a Hierarchical Back Projection Network (HBPN), that cascades multiple HourGlass (HG) modules to bottom-up and top-down process features across all scales to capture various spatial correlations and then consolidates the best representation for reconstruction. We adopt the back projection blocks in our proposed network to provide the error correlated up and down-sampling process to replace simple deconvolution and pooling process for better estimation. A new Softmax based Weighted Reconstruction (WR) process is used to combine the outputs of HG modules to further improve super-resolution. Experimental results on various datasets (including the validation dataset, NTIRE2019, of the Real Image Super-resolution Challenge) show that our proposed approach can achieve and improve the performance of the state-of-the-art methods for different scaling factors.