A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models
This addresses the issue of visual artifacts in super-resolution for image and video processing, but it is incremental as it builds on existing GAN frameworks.
The paper tackles the problem of artifacts and noise in GAN-based super-resolution models by proposing a general method to incorporate spatial information into loss functions, resulting in enhanced perceptual quality and reduced side effects.
Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs, such as unexpected artifacts and noises. To reduce these artifacts and enhance the perceptual quality of the results, in this paper, we propose a general method that can be effectively used in most GAN-based super-resolution (SR) models by introducing essential spatial information into the training process. We extract spatial information from the input data and incorporate it into the training loss, making the corresponding loss a spatially adaptive (SA) one. After that, we utilize it to guide the training process. We will show that the proposed approach is independent of the methods used to extract the spatial information and independent of the SR tasks and models. This method consistently guides the training process towards generating visually pleasing SR images and video frames, substantially mitigating artifacts and noise, ultimately leading to enhanced perceptual quality.