Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts

arXiv:2402.19215v1 Announce Type: cross
Abstract: Super-resolution (SR) is an ill-posed inverse problem, where the size of the set of feasible solutions that are consistent with a given low-resolution image is very large. Many algorithms have been proposed to find a "good" solution among the feasible solutions that strike a balance between fidelity and perceptual quality. Unfortunately, all known methods generate artifacts and hallucinations while trying to reconstruct high-frequency (HF) image details. A fundamental question is: Can a model learn to …

abstract algorithms arxiv consistent control cs.cv domain eess.iv generative good image losses low set solution solutions training type wavelet