Improving Super-Resolution Methods via Incremental Residual Learning
This work addresses performance bottlenecks in super-resolution for image processing applications, but it is incremental as it builds upon existing methods.
The paper tackles the limitations of existing super-resolution methods in modeling high-frequency information and transitioning from low to high resolution by proposing an Incremental Residual Learning (IRL) framework, which consistently improves state-of-the-art methods on public benchmarks with only about a 20% increase in training time.
Recently, Convolutional Neural Networks (CNNs) have shown promising performance in super-resolution (SR). However, these methods operate primarily on Low Resolution (LR) inputs for memory efficiency but this limits, as we demonstrate, their ability to (i) model high frequency information; and (ii) smoothly translate from LR to High Resolution (HR) space. To this end, we propose a novel Incremental Residual Learning (IRL) framework to address these mentioned issues. In IRL, first we select a typical SR pre-trained network as a master branch. Next we sequentially train and add residual branches to the main branch, where each residual branch is learned to model accumulated residuals of all previous branches. We plug state of the art methods in IRL framework and demonstrate consistent performance improvement on public benchmark datasets to set a new state of the art for SR at only approximately 20% increase in training time.