In-Person Oral presentation / top 25% paper

Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

Yinhuai Wang · Jiwen Yu · Jian Zhang

[ Abstract ] [ Livestream: Visit Oral 6 Track 4: Applications & Social Aspects of Machine Learning & General Machine Learning ]
Wed 3 May 6:40 a.m. — 6:50 a.m. PDT

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.

Chat is not available.