Frequency Domain-based Perceptual Loss for Super Resolution
This addresses the problem of improving perceptual quality in super resolution for image processing applications, but it is incremental as it builds on existing loss functions by shifting to the frequency domain.
The paper tackles single image super resolution by introducing a frequency domain perceptual loss (FDPL) that prioritizes frequencies related to human perception, resulting in a higher average PSNR of 30.94 compared to 30.59 with pixel loss on the Set5 dataset.
We introduce Frequency Domain Perceptual Loss (FDPL), a loss function for single image super resolution (SR). Unlike previous loss functions used to train SR models, which are all calculated in the pixel (spatial) domain, FDPL is computed in the frequency domain. By working in the frequency domain we can encourage a given model to learn a mapping that prioritizes those frequencies most related to human perception. While the goal of FDPL is not to maximize the Peak Signal to Noise Ratio (PSNR), we found that there is a correlation between decreasing FDPL and increasing PSNR. Training a model with FDPL results in a higher average PSRN (30.94), compared to the same model trained with pixel loss (30.59), as measured on the Set5 image dataset. We also show that our method achieves higher qualitative results, which is the goal of a perceptual loss function. However, it is not clear that the improved perceptual quality is due to the slightly higher PSNR or the perceptual nature of FDPL.