Causal Disentanglement for Full-Reference Image Quality Assessment

• URL: http://arxiv.org/abs/2604.21654v2
• Date: Wed, 29 Apr 2026 07:26:38 GMT
• Title: Causal Disentanglement for Full-Reference Image Quality Assessment
• Abstract summary: We propose a novel FR-IQA paradigm based on causal inference and decoupled representation learning.<n>Our approach formulates degradation estimation as a causal disentanglement process guided by intervention on latent representations.<n>Our method achieves highly competitive performance on standard IQA benchmarks across fully supervised, few-label, and label-free settings.
• Score: 21.96346718260435
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Existing deep network-based full-reference image quality assessment (FR-IQA) models typically work by performing pairwise comparisons of deep features from the reference and distorted images. In this paper, we approach this problem from a different perspective and propose a novel FR-IQA paradigm based on causal inference and decoupled representation learning. Unlike typical feature comparison-based FR-IQA models, our approach formulates degradation estimation as a causal disentanglement process guided by intervention on latent representations. We first decouple degradation and content representations by exploiting the content invariance between the reference and distorted images. Second, inspired by the human visual masking effect, we design a masking module to model the causal relationship between image content and degradation features, thereby extracting content-influenced degradation features from distorted images. Finally, quality scores are predicted from these degradation features using either supervised regression or label-free dimensionality reduction. Extensive experiments demonstrate that our method achieves highly competitive performance on standard IQA benchmarks across fully supervised, few-label, and label-free settings. Furthermore, we evaluate the approach on diverse non-standard natural image domains with scarce data, including underwater, radiographic, medical, neutron, and screen-content images. Benefiting from its ability to perform scenario-specific training and prediction without labeled IQA data, our method exhibits superior cross-domain generalization compared to existing training-free FR-IQA models.

Related papers

• Plug In, Grade Right: Psychology-Inspired AGIQA [60.23968344837525]
  Existing AGIQA models estimate image quality by measuring and aggregating similarities between image embeddings and text embeddings.<n>We propose an improved Graded Response Model (GRM) for AGIQA.<n>Our Arithmetic GRM based Quality Grading (AGQG) module enjoys a plug-and-play advantage.
  arXiv  Detail & Related papers  (2025-12-28T04:51:05Z)
• Q-Insight: Understanding Image Quality via Visual Reinforcement Learning [27.26829134776367]
  Image quality assessment (IQA) focuses on the perceptual visual quality of images, playing a crucial role in downstream tasks such as image reconstruction, compression, and generation.<n>We propose Q-Insight, a reinforcement learning-based model built upon group relative policy optimization (GRPO)<n>We show that Q-Insight substantially outperforms existing state-of-the-art methods in both score regression and degradation perception tasks.
  arXiv  Detail & Related papers  (2025-03-28T17:59:54Z)
• Dual-Representation Interaction Driven Image Quality Assessment with Restoration Assistance [11.983231834400698]
  No-Reference Image Quality Assessment for distorted images has always been a challenging problem due to image content variance and distortion diversity. Previous IQA models mostly encode explicit single-quality features of synthetic images to obtain quality-aware representations for quality score prediction. We introduce the DRI method to obtain degradation vectors and quality vectors of images, which separately model the degradation and quality information of low-quality images.
  arXiv  Detail & Related papers  (2024-11-26T12:48:47Z)
• Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement [12.628718661568048]
  We aim to explore a generalized human visual attention estimation strategy to mimic the process of human quality rating. In particular, we model human attention generation by measuring the statistical dependency between the degraded image and the reference image. Experimental results verify the performance of existing IQA models can be consistently improved when our attention module is incorporated.
  arXiv  Detail & Related papers  (2024-08-19T11:55:32Z)
• DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild [73.6767681305851]
  Blind image quality assessment (IQA) in the wild presents significant challenges.<n>Given the difficulty in collecting large-scale training data, leveraging limited data to develop a model with strong generalization remains an open problem.<n>Motivated by the robust image perception capabilities of pre-trained text-to-image (T2I) diffusion models, we propose a novel IQA method, diffusion priors-based IQA.
  arXiv  Detail & Related papers  (2024-05-30T12:32:35Z)
• Contrastive Pre-Training with Multi-View Fusion for No-Reference Point Cloud Quality Assessment [49.36799270585947]
  No-reference point cloud quality assessment (NR-PCQA) aims to automatically evaluate the perceptual quality of distorted point clouds without available reference. We propose a novel contrastive pre-training framework tailored for PCQA (CoPA) Our method outperforms the state-of-the-art PCQA methods on popular benchmarks.
  arXiv  Detail & Related papers  (2024-03-15T07:16:07Z)
• When No-Reference Image Quality Models Meet MAP Estimation in Diffusion Latents [92.45867913876691]
  No-reference image quality assessment (NR-IQA) models can effectively quantify perceived image quality.<n>We show that NR-IQA models can be plugged into the maximum a posteriori (MAP) estimation framework for image enhancement.
  arXiv  Detail & Related papers  (2024-03-11T03:35:41Z)
• Diffusion Model Based Visual Compensation Guidance and Visual Difference Analysis for No-Reference Image Quality Assessment [78.21609845377644]
  We propose a novel class of state-of-the-art (SOTA) generative model, which exhibits the capability to model intricate relationships.<n>We devise a new diffusion restoration network that leverages the produced enhanced image and noise-containing images.<n>Two visual evaluation branches are designed to comprehensively analyze the obtained high-level feature information.
  arXiv  Detail & Related papers  (2024-02-22T09:39:46Z)
• ARNIQA: Learning Distortion Manifold for Image Quality Assessment [28.773037051085318]
  No-Reference Image Quality Assessment (NR-IQA) aims to develop methods to measure image quality in alignment with human perception without the need for a high-quality reference image. We propose a self-supervised approach named ARNIQA for modeling the image distortion manifold to obtain quality representations in an intrinsic manner.
  arXiv  Detail & Related papers  (2023-10-20T17:22:25Z)
• Regression-free Blind Image Quality Assessment with Content-Distortion Consistency [42.683300312253884]
  We propose a regression-free framework for image quality evaluation. It is based upon retrieving locally similar instances by incorporating semantic and distortion feature spaces. The proposed method achieves competitive, even superior performance compared to state-of-the-art regression-based methods.
  arXiv  Detail & Related papers  (2023-07-18T14:19:28Z)
• Image Quality Assessment using Contrastive Learning [50.265638572116984]
  We train a deep Convolutional Neural Network (CNN) using a contrastive pairwise objective to solve the auxiliary problem. We show through extensive experiments that CONTRIQUE achieves competitive performance when compared to state-of-the-art NR image quality models. Our results suggest that powerful quality representations with perceptual relevance can be obtained without requiring large labeled subjective image quality datasets.
  arXiv  Detail & Related papers  (2021-10-25T21:01:00Z)
• Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild [98.48284827503409]
  We develop a textitunified BIQA model and an approach of training it for both synthetic and realistic distortions. We employ the fidelity loss to optimize a deep neural network for BIQA over a large number of such image pairs. Experiments on six IQA databases show the promise of the learned method in blindly assessing image quality in the laboratory and wild.
  arXiv  Detail & Related papers  (2020-05-28T13:35:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.