Timezone: »

GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration
Naoki Murata · Koichi Saito · Chieh-Hsin Lai · Yuhta Takida · Toshimitsu Uesaka · Yuki Mitsufuji · Stefano Ermon

Tue Jul 25 09:18 PM -- 09:26 PM (PDT) @ Ballroom A

Pre-trained diffusion models have been successfully used as priors in a variety of linear inverse problems, where the goal is to reconstruct a signal from noisy linear measurements. However, existing approaches require knowledge of the linear operator. In this paper, we propose GibbsDDRM, an extension of Denoising Diffusion Restoration Models (DDRM) to a blind setting in which the linear measurement operator is unknown. GibbsDDRM constructs a joint distribution of the data, measurements, and linear operator by using a pre-trained diffusion model for the data prior, and it solves the problem by posterior sampling with an efficient variant of a Gibbs sampler. The proposed method is problem-agnostic, meaning that a pre-trained diffusion model can be applied to various inverse problems without fine-tuning. In experiments, it achieved high performance on both blind image deblurring and vocal dereverberation tasks, despite the use of simple generic priors for the underlying linear operators.

Author Information

Naoki Murata (Sony Group Corporation)
Koichi Saito (Sony Group Corporation, Tokyo)
Chieh-Hsin Lai (Sony AI)
Yuhta Takida (Sony Group Corporation)
Toshimitsu Uesaka (Sony Group Corporation)
Yuki Mitsufuji (Sony Group Corporation)
Stefano Ermon (Stanford University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors