AI RESEARCH
Image Restoration via Diffusion Models with Dynamic Resolution
arXiv CS.CV
•
ArXi:2605.14267v1 Announce Type: new Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within the high-dimensional pixel space, resulting in high computational overhead. While methods based on latent DMs seek to alleviate this issue by utilizing the compressed latent space of a variational autoencoder, they require repeated encoder-decoder inference. This