# Causal Disentanglement-Inspired Degradation Representation Learning for Full-Reference Image Quality Assessment

arXiv: https://arxiv.org/abs/2604.21654 · HTML: https://mlsanity.com/paper/2604.21654/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 66 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [PieAPP: Perceptual Image-Error Assessment through Pairwise Preference](https://mlsanity.com/paper/1806.02067/) (2018)
- [Weakly Supervised Disentangled Generative Causal Representation Learning](https://mlsanity.com/paper/2010.02637/) (2020)
- [Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network](https://mlsanity.com/paper/2204.10485/) (2022)
- [Perceptual Image Quality Assessment with Transformers](https://mlsanity.com/paper/2104.14730/) (2021)
- [Continual Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/2102.09717/) (2021)
- [Locally Adaptive Structure and Texture Similarity for Image Quality Assessment](https://mlsanity.com/paper/2110.08521/) (2021)
- [Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop](https://mlsanity.com/paper/2210.00933/) (2022)
- [Projected Distribution Loss for Image Enhancement](https://mlsanity.com/paper/2012.09289/) (2020)
- [Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment](https://mlsanity.com/paper/2003.03849/) (2020)
- [DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space](https://mlsanity.com/paper/2208.03323/) (2022)
- [DeepDC: Deep Distance Correlation as a Perceptual Image Quality Evaluator](https://mlsanity.com/paper/2211.04927/) (2022)
- [Measuring Perceptual Color Differences of Smartphone Photographs](https://mlsanity.com/paper/2205.13489/) (2022)
- [Image Quality Assessment: Investigating Causal Perceptual Effects with Abductive Counterfactual Inference](https://mlsanity.com/paper/2412.16939/) (2024)
- [Full-reference image quality assessment by combining global and local distortion measures](https://mlsanity.com/paper/1412.5488/) (2014)
- [SCADI: Self-supervised Causal Disentanglement in Latent Variable Models](https://mlsanity.com/paper/2311.06567/) (2023)

## Abstract (arXiv)

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.