Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
arXiv:2212.00490
Abstract
Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators. In this work, we propose the Denoising Diffusion Null-Space Model (DDNM), a novel zero-shot framework for arbitrary linear IR problems, including but not limited to image super-resolution, colorization, inpainting, compressed sensing, and deblurring. DDNM only needs a pre-trained off-the-shelf diffusion model as the generative prior, without any extra training or network modifications. By refining only the null-space contents during the reverse diffusion process, we can yield diverse results satisfying both data consistency and realness. We further propose an enhanced and robust version, dubbed DDNM+, to support noisy restoration and improve restoration quality for hard tasks. Our experiments on several IR tasks reveal that DDNM outperforms other state-of-the-art zero-shot IR methods. We also demonstrate that DDNM+ can solve complex real-world applications, e.g., old photo restoration.
Cited by in corpus (7)
- Diffusion Models, Image Super-Resolution And Everything: A Survey
- 360-Degree Panorama Generation from Few Unregistered NFoV Images
- A review of advancements in low-light image enhancement using deep learning
- Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization
- Super-resolution Reconstruction of Single Image for Latent features
- Score-Based Diffusion Models for Photoacoustic Tomography Image Reconstruction
- Diffusion-Based Audio Inpainting