Suppressing Uncertainties in Degradation Estimation for Blind Super-Resolution

arXiv:2406.16459v1 Announce Type: new
Abstract: The problem of blind image super-resolution aims to recover high-resolution (HR) images from low-resolution (LR) images with unknown degradation modes. Most existing methods model the image degradation process using blur kernels. However, this explicit modeling approach struggles to cover the complex and varied degradation processes encountered in the real world, such as high-order combinations of JPEG compression, blur, and noise. Implicit modeling for the degradation process can effectively overcome this issue, but a key challenge …

abstract arxiv blind cs.cv however image images low modeling problem process processes resolution type