A Fully Progressive Approach to Single-Image Super-Resolution
This work addresses the problem of efficient and high-quality image upscaling for computer vision applications, representing an incremental improvement with a focus on speed and scalability.
The paper tackles the challenge of achieving high-quality single-image super-resolution at large upsampling factors by proposing a progressive method (ProSR) that upsamples images in steps and uses curriculum learning, resulting in competitive performance (2nd in SSIM, 4th in PSNR) and 5x faster runtime compared to the top model.
Recent deep learning approaches to single image super-resolution have achieved impressive results in terms of traditional error measures and perceptual quality. However, in each case it remains challenging to achieve high quality results for large upsampling factors. To this end, we propose a method (ProSR) that is progressive both in architecture and training: the network upsamples an image in intermediate steps, while the learning process is organized from easy to hard, as is done in curriculum learning. To obtain more photorealistic results, we design a generative adversarial network (GAN), named ProGanSR, that follows the same progressive multi-scale design principle. This not only allows to scale well to high upsampling factors (e.g., 8x) but constitutes a principled multi-scale approach that increases the reconstruction quality for all upsampling factors simultaneously. In particular ProSR ranks 2nd in terms of SSIM and 4th in terms of PSNR in the NTIRE2018 SISR challenge [34]. Compared to the top-ranking team, our model is marginally lower, but runs 5 times faster.