# SwinIQA: Learned Swin Distance for Compressed Image Quality Assessment

arXiv: https://arxiv.org/abs/2205.04264 · HTML: https://mlsanity.com/paper/2205.04264/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 9 May 2022.

## Builds on (most cited first, 10 of 10)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [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)
- [Transformer for Image Quality Assessment](https://mlsanity.com/paper/2101.01097/) (2020)
- [Perceptual Image Quality Assessment with Transformers](https://mlsanity.com/paper/2104.14730/) (2021)
- [Learned Block-based Hybrid Image Compression](https://mlsanity.com/paper/2012.09550/) (2020)
- [LIQA: Lifelong Blind Image Quality Assessment](https://mlsanity.com/paper/2104.14115/) (2021)

## Built on by (most cited first, 14 of 14)

- [KVQ: Kwai Video Quality Assessment for Short-form Videos](https://mlsanity.com/paper/2402.07220/) (2024)
- [NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results](https://mlsanity.com/paper/2404.11313/) (2024)
- [HST: Hierarchical Swin Transformer for Compressed Image Super-resolution](https://mlsanity.com/paper/2208.09885/) (2022)
- [DeepDC: Deep Distance Correlation as a Perceptual Image Quality Evaluator](https://mlsanity.com/paper/2211.04927/) (2022)
- [Attacking Perceptual Similarity Metrics](https://mlsanity.com/paper/2305.08840/) (2023)
- [RTN: Reinforced Transformer Network for Coronary CT Angiography Vessel-level Image Quality Assessment](https://mlsanity.com/paper/2207.06177/) (2022)
- [Semantic-aware Message Broadcasting for Efficient Unsupervised Domain Adaptation](https://mlsanity.com/paper/2212.02739/) (2022)
- [AIM 2024 Challenge on Video Super-Resolution Quality Assessment: Methods and Results](https://mlsanity.com/paper/2410.04225/) (2024)
- [BiRQA: Bidirectional Robust Quality Assessment for Images](https://mlsanity.com/paper/2602.20351/) (2026)
- [Learned Lossless JPEG Transcoding via Joint Lossy and Residual Compression](https://mlsanity.com/paper/2208.11673/) (2022)
- [Mask Reference Image Quality Assessment](https://mlsanity.com/paper/2302.13770/) (2023)
- [Progressive Feature Fusion Network for Enhancing Image Quality Assessment](https://mlsanity.com/paper/2401.06992/) (2024)
- [Priorformer: A UGC-VQA Method with content and distortion priors](https://mlsanity.com/paper/2406.16297/) (2024)
- [Image Quality Assessment: Exploring Quality Awareness via Memory-driven Distortion Patterns Matching](https://mlsanity.com/paper/2602.18000/) (2026)

## Abstract (arXiv)

Image compression has raised widespread interest recently due to its significant importance for multimedia storage and transmission. Meanwhile, a reliable image quality assessment (IQA) for compressed images can not only help to verify the performance of various compression algorithms but also help to guide the compression optimization in turn. In this paper, we design a full-reference image quality assessment metric SwinIQA to measure the perceptual quality of compressed images in a learned Swin distance space. It is known that the compression artifacts are usually non-uniformly distributed with diverse distortion types and degrees. To warp the compressed images into the shared representation space while maintaining the complex distortion information, we extract the hierarchical feature representations from each stage of the Swin Transformer. Besides, we utilize cross attention operation to map the extracted feature representations into a learned Swin distance space. Experimental results show that the proposed metric achieves higher consistency with human's perceptual judgment compared with both traditional methods and learning-based methods on CLIC datasets.