AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation

arXiv:2404.01717v2 Announce Type: replace
Abstract: Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs. However, their practical applicability is often hampered by poor efficiency, stemming from the requirement of thousands or hundreds of sampling steps. Inspired by the efficient text-to-image approach adversarial diffusion distillation (ADD), we design AddSR to address this issue by incorporating the ideas of both distillation and ControlNet. Specifically, we first propose a prediction-based …

abstract adversarial arxiv blind capabilities clear cs.cv diffusion distillation eess.iv efficiency generative however images inputs low practical resolution sampling stable diffusion stemming type