Real-World Super-Resolution of Face-Images from Surveillance Cameras
Most SR methods are trained on LR (low resolution) data, which is downsampled from HR (high resolution) data using bicubic interpolation, but real-life LR images are usually different, so models work worse on them. In this paper, the authors suggest using blur kernels, noise, and JPEG compression artifacts to generate LR images similar to the original ones.
Another suggested improvement is using ESRGAN and replacing VGG-loss with LPIPS-loss, as well as adding PatchGAN.
In addition, the authors show that NIMA metric better correlates with human perception (mean opinion rank) than traditional Image Quality Assessment methods.
Paper: https://arxiv.org/abs/2102.03113
#deeplearning #superresolution #gan #facesuperresolution
Most SR methods are trained on LR (low resolution) data, which is downsampled from HR (high resolution) data using bicubic interpolation, but real-life LR images are usually different, so models work worse on them. In this paper, the authors suggest using blur kernels, noise, and JPEG compression artifacts to generate LR images similar to the original ones.
Another suggested improvement is using ESRGAN and replacing VGG-loss with LPIPS-loss, as well as adding PatchGAN.
In addition, the authors show that NIMA metric better correlates with human perception (mean opinion rank) than traditional Image Quality Assessment methods.
Paper: https://arxiv.org/abs/2102.03113
#deeplearning #superresolution #gan #facesuperresolution
