Super-resolution image with unknown degradation using high resolution for refinement with AddSR
Super-resolution image with unknown degradation using high resolution for refinement with AddSR
AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation
arXiv paper abstract https://arxiv.org/abs/2404.01717
arXiv PDF paper https://arxiv.org/pdf/2404.01717.pdf
Blind super-resolution methods based on stable diffusion showcase formidable ... capabilities ... However ... often hampered by poor efficiency ... from ... thousands ... of sampling steps.
Inspired by the efficient text-to-image approach adversarial diffusion distillation (ADD), ... design AddSR to address this issue by ... the ideas of both distillation and ControlNet.
... first propose a prediction-based self-refinement strategy to provide high-frequency information in the student model output with marginal additional time cost.
... refine the training process by employing HR images, rather than LR images, to regulate the teacher model, providing a more robust constraint for distillation.
... introduce a timestep-adapting loss to address the perception-distortion imbalance problem introduced by ADD.
... AddSR generates better restoration results, while achieving faster speed than previous SD-based state-of-the-art models (e.g., 7x faster than SeeSR).
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Комментарии