2025-01-14-meng25a.md

title	booktitle	year	volume	series	month	publisher	pdf	url	software	openreview	abstract	layout	issn	id	tex_title	firstpage	lastpage	page	order	cycles	bibtex_editor	editor	bibtex_author	author	date	address	container-title	genre	issued	extras
Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems	Proceedings of the 16th Asian Conference on Machine Learning	2025	260	Proceedings of Machine Learning Research	0	PMLR	https://raw.githubusercontent.com/mlresearch/v260/main/assets/meng25a/meng25a.pdf	https://proceedings.mlr.press/v260/meng25a.html	https://github.com/mengxiangming/dmps	A07d0PMRqc	With the rapid development of diffusion models and flow-based generative models, there has been a surge of interests in solving noisy linear inverse problems, e.g., super-resolution, deblurring, denoising, colorization, etc, with generative models. However, while remarkable reconstruction performances have been achieved, their inference time is typically too slow since most of them rely on the seminal diffusion posterior sampling (DPS) framework and thus to approximate the intractable likelihood score, time-consuming gradient calculation through back-propagation is needed. To address this issue, this paper provides a fast and effective solution by proposing a simple closed-form approximation to the likelihood score. For both diffusion and flow-based models, extensive experiments are conducted on various noisy linear inverse problems such as noisy super-resolution, denoising, deblurring, and colorization. In all these tasks, our method (namely DMPS) demonstrates highly competitive or even better reconstruction performances while being significantly faster than all the baseline methods.	inproceedings	2640-3498	meng25a	Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems	623	638	623-638	623	false	Nguyen, Vu and Lin, Hsuan-Tien	given family Vu Nguyen given family Hsuan-Tien Lin	Meng, Xiangming and Kabashima, Yoshiyuki	given family Xiangming Meng given family Yoshiyuki Kabashima	2025-01-14		Proceedings of the 16th Asian Conference on Machine Learning	inproceedings	date-parts 2025 1 14	label link Supplementary PDF https://raw.githubusercontent.com/mlresearch/v260/main/assets/assets/meng25a/meng25a-supp.pdf