Can I read Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior on EtoBox?

Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior by Xu, Tongda; Cai, Xiyan; Zhang, Xinjie; Ge, Xingtong; He, Dailan; Sun, Ming; Liu, Jingjing; Zhang, Ya-Qin; Li, Jian; Wang, Yan is a scholarly article available to read on EtoBox.

What is Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior about?

Recent advancements in diffusion models have been leveraged to address inverse problems without additional training, and Diffusion Posterior Sampling (DPS) (Chung et al., 2022a) is among the most popular approaches. Previous analyses suggest that DPS accomplishes posterior sampling by approximating the conditional score. While in this paper, we demonstrate that the conditional score approximation employed by DPS is not as effective as previously assumed, but rather aligns more closely with the principle of maximizing a posterior (MAP). This assertion is substantiated through an examination of DPS on 512x512 ImageNet images, revealing that: 1) DPS's conditional score estimation significantly diverges from the score of a well-trained conditional diffusion model and is even inferior to the unconditional score; 2) The mean of DPS's conditional score estimation deviates significantly from zero, rendering it an invalid score estimation; 3) DPS generates high-quality samples with significantly lower diversity. In light of the above findings, we posit that DPS more closely resembles MAP than a conditional score estimator, and accordingly propose the following enhancements to DPS: 1) we exp

Author

Xu, Tongda; Cai, Xiyan; Zhang, Xinjie; Ge, Xingtong; He, Dailan; Sun, Ming; Liu, Jingjing; Zhang, Ya-Qin; Li, Jian; Wang, Yan

Published

2025

Language

EN