# Vision Language Modeling of Content, Distortion and Appearance for Image Quality Assessment

arXiv: https://arxiv.org/abs/2406.09858 · HTML: https://mlsanity.com/paper/2406.09858/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 7 of its 65 references that are in the map.
- First posted on arXiv 14 Jun 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)

## Builds on (most cited first, 7 of 7)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning](https://mlsanity.com/paper/2001.08113/) (2020)
- [A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction](https://mlsanity.com/paper/1708.08190/) (2017)
- [Deep Neural Networks for Blind Image Quality Assessment: Addressing the Data Challenge](https://mlsanity.com/paper/2109.12161/) (2021)

## Built on by (most cited first, 4 of 4)

- [HiRQA: Hierarchical Ranking and Quality Alignment for Opinion-Unaware Image Quality Assessment](https://mlsanity.com/paper/2508.15130/) (2025)
- [Enhancing Wide-Angle Image Using Narrow-Angle View of the Same Scene](https://mlsanity.com/paper/2504.09455/) (2025)
- [Life-IQA: Boosting Blind Image Quality Assessment through GCN-enhanced Layer Interaction and MoE-based Feature Decoupling](https://mlsanity.com/paper/2511.19024/) (2025)
- [Linear Fusion MultiDiffusion for Fast Training-Free Spherical Panorama Generation](https://mlsanity.com/paper/2609.01997/) (2026)

## Abstract (arXiv)

The visual quality of an image is confounded by a number of intertwined factors including its semantic content, distortion characteristics and appearance properties such as brightness, contrast, sharpness, and colourfulness. Distilling high level knowledge about all these quality bearing attributes is crucial for developing objective Image Quality Assessment (IQA).While existing solutions have modeled some of these aspects, a comprehensive solution that involves all these important quality related attributes has not yet been developed. In this paper, we present a new blind IQA (BIQA) model termed Self-supervision and Vision-Language supervision Image QUality Evaluator (SLIQUE) that features a joint vision-language and visual contrastive representation learning framework for acquiring high level knowledge about the images semantic contents, distortion characteristics and appearance properties for IQA. For training SLIQUE, we have developed a systematic approach to constructing a first of its kind large image database annotated with all three categories of quality relevant texts. The Text Annotated Distortion, Appearance and Content (TADAC) database has over 1.6 million images annotated with textual descriptions of their semantic contents, distortion characteristics and appearance properties. The method for constructing TADAC and the database itself will be particularly useful for exploiting vision-language modeling for advanced IQA applications. Extensive experimental results show that SLIQUE has superior performances over state of the art, demonstrating the soundness of its design principle and the effectiveness of its implementation.