Back to Search Start Over

G2D2: Gradient-guided Discrete Diffusion for image inverse problem solving

Authors :
Murata, Naoki
Lai, Chieh-Hsin
Takida, Yuhta
Uesaka, Toshimitsu
Nguyen, Bac
Ermon, Stefano
Mitsufuji, Yuki
Publication Year :
2024

Abstract

Recent literature has effectively utilized diffusion models trained on continuous variables as priors for solving inverse problems. Notably, discrete diffusion models with discrete latent codes have shown strong performance, particularly in modalities suited for discrete compressed representations, such as image and motion generation. However, their discrete and non-differentiable nature has limited their application to inverse problems formulated in continuous spaces. This paper presents a novel method for addressing linear inverse problems by leveraging image-generation models based on discrete diffusion as priors. We overcome these limitations by approximating the true posterior distribution with a variational distribution constructed from categorical distributions and continuous relaxation techniques. Furthermore, we employ a star-shaped noise process to mitigate the drawbacks of traditional discrete diffusion models with absorbing states, demonstrating that our method performs comparably to continuous diffusion techniques. To the best of our knowledge, this is the first approach to use discrete diffusion model-based priors for solving image inverse problems.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2410.14710
Document Type :
Working Paper