cs.CVMar 11, 2024

When No-Reference Image Quality Models Meet MAP Estimation in Diffusion Latents

Authors: Weixia Zhang, Dingquan Li, Guangtao Zhai, Xiaokang Yang, Kede Ma

Organizations: MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China · Department of Networked Intelligence, Pengcheng Laboratory, Shenzhen, China · Department of Computer Science and Shenzhen Research Institute, City University of Hong Kong, Kowloon, Hong Kong

Abstract

Contemporary no-reference image quality assessment (NR-IQA) models can effectively quantify perceived image quality, often achieving strong correlations with human perceptual scores on standard IQA benchmarks. Yet, limited efforts have been devoted to treating NR-IQA models as natural image priors for real-world image enhancement, and consequently comparing them from a perceptual optimization standpoint. In this work, we show -- for the first time -- that NR-IQA models can be plugged into the maximum a posteriori (MAP) estimation framework for image enhancement. This is achieved by performing gradient ascent in the diffusion latent space rather than in the raw pixel domain, leveraging a pretrained differentiable and bijective diffusion process. Likely, different NR-IQA models lead to different enhanced outputs, which in turn provides a new computational means of comparing them. Unlike conventional correlation-based measures, our comparison method offers complementary insights into the respective strengths and weaknesses of the competing NR-IQA models in perceptual optimization scenarios. Additionally, we aim to improve the best-performing NR-IQA model in diffusion latent MAP estimation by incorporating the advantages of other top-performing methods. The resulting model delivers noticeably better results in enhancing real-world images afflicted by unknown and complex distortions, all preserving a high degree of image fidelity.

Figures & tables

Explore similar work

CardsList
  1. Preference-Guided Debiasing for No-Reference Enhancement Image Quality Assessment

    Mar 20, 2026Shiqi Gao, Kang Fu, Zitong Xu +4Image Quality AssessmentDebiased ML

  2. Boosting Image Quality Assessment Performance: Unsupervised Score Fusion by Deep Maximum a Posteriori Estimation

    May 28, 2026Zhongling Wang, Raymond Zhou, Shahrukh Athar +2Image Quality AssessmentMAP Estimation

  3. SHAMISA: SHAped Modeling of Implicit Structural Associations for Self-supervised No-Reference Image Quality Assessment

    Mar 14, 2026Mahdi Naseri, Zhou WangImage Quality AssessmentSelf-Supervised Learning