Saved in:
Bibliographic Details
Main Authors: Zhang, Jiawei, Liu, Ziyuan, Yan, Leon, Xiao, Zhenyu, Gu, Yuantao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.28711
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910270078582784
author Zhang, Jiawei
Liu, Ziyuan
Yan, Leon
Xiao, Zhenyu
Gu, Yuantao
author_facet Zhang, Jiawei
Liu, Ziyuan
Yan, Leon
Xiao, Zhenyu
Gu, Yuantao
contents The distortion-perception (D-P) tradeoff is a fundamental phenomenon of Bayesian inverse problems, which characterizes the inherent tension between distortion performance and perceptual quality. Enabling flexible traversal of the D-P tradeoff at inference time is crucial for practical applications. Despite the recent success of diffusion models in zero-shot inverse problem solving, efficient and principled strategies for D-P traversal in diffusion-based inverse algorithms remain inadequately characterized. In this paper, we propose a stage-wise framework for realizing D-P traversal using a single diffusion model in zero-shot inverse problems. Our proposed method, termed MAP-RPS, starts with an MAP estimation stage that approximates the MMSE solution and provides a low-distortion initialization, followed by a re-noised posterior sampling stage that progressively improves perceptual quality. We provide theoretical analyses for both stages, establishing the validity and effectiveness of the proposed design. Furthermore, we extend MAP-RPS to the latent space, yielding LMAP-RPS, which enjoys broader applicability by leveraging large-scale pre-trained latent diffusion backbones. Extensive experiments demonstrate that MAP-RPS and LMAP-RPS enable more effective D-P traversal on various tasks, while also exhibiting strong performance as efficient solvers for real-world inverse problems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_28711
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion Models
Zhang, Jiawei
Liu, Ziyuan
Yan, Leon
Xiao, Zhenyu
Gu, Yuantao
Machine Learning
The distortion-perception (D-P) tradeoff is a fundamental phenomenon of Bayesian inverse problems, which characterizes the inherent tension between distortion performance and perceptual quality. Enabling flexible traversal of the D-P tradeoff at inference time is crucial for practical applications. Despite the recent success of diffusion models in zero-shot inverse problem solving, efficient and principled strategies for D-P traversal in diffusion-based inverse algorithms remain inadequately characterized. In this paper, we propose a stage-wise framework for realizing D-P traversal using a single diffusion model in zero-shot inverse problems. Our proposed method, termed MAP-RPS, starts with an MAP estimation stage that approximates the MMSE solution and provides a low-distortion initialization, followed by a re-noised posterior sampling stage that progressively improves perceptual quality. We provide theoretical analyses for both stages, establishing the validity and effectiveness of the proposed design. Furthermore, we extend MAP-RPS to the latent space, yielding LMAP-RPS, which enjoys broader applicability by leveraging large-scale pre-trained latent diffusion backbones. Extensive experiments demonstrate that MAP-RPS and LMAP-RPS enable more effective D-P traversal on various tasks, while also exhibiting strong performance as efficient solvers for real-world inverse problems.
title Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion Models
topic Machine Learning
url https://arxiv.org/abs/2605.28711