# Learning to Blindly Assess Image Quality in the Laboratory and Wild

arXiv: https://arxiv.org/abs/1907.00516 · HTML: https://mlsanity.com/paper/1907.00516/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2019.

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

- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [NTIRE 2022 Challenge on Perceptual Image Quality Assessment](https://mlsanity.com/paper/2206.11695/) (2022)
- [Continual Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/2102.09717/) (2021)
- [Deep Neural Network for Blind Visual Quality Assessment of 4K Content](https://mlsanity.com/paper/2206.04363/) (2022)
- [An Image Quality Assessment Dataset for Portraits](https://mlsanity.com/paper/2304.05772/) (2023)
- [MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion](https://mlsanity.com/paper/2205.10101/) (2022)
- [Optimization-Based Improvement of Face Image Quality Assessment Techniques](https://mlsanity.com/paper/2305.14856/) (2023)
- [GMC-IQA: Exploiting Global-correlation and Mean-opinion Consistency for No-reference Image Quality Assessment](https://mlsanity.com/paper/2401.10511/) (2024)
- [Forgetting to Remember: A Scalable Incremental Learning Framework for Cross-Task Blind Image Quality Assessment](https://mlsanity.com/paper/2209.07126/) (2022)
- [Generalized Portrait Quality Assessment](https://mlsanity.com/paper/2402.09178/) (2024)
- [Cross-Dataset-Robust Method for Blind Real-World Image Quality Assessment](https://mlsanity.com/paper/2309.14868/) (2023)
- [Pairwise Comparisons Are All You Need](https://mlsanity.com/paper/2403.09746/) (2024)
- [MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge Distillation](https://mlsanity.com/paper/2409.01212/) (2024)
- [Towards Unified Video Quality Assessment](https://mlsanity.com/paper/2512.02224/) (2025)

## Abstract (arXiv)

Computational models for blind image quality assessment (BIQA) are typically trained in well-controlled laboratory environments with limited generalizability to realistically distorted images. Similarly, BIQA models optimized for images captured in the wild cannot adequately handle synthetically distorted images. To face the cross-distortion-scenario challenge, we develop a BIQA model and an approach of training it on multiple IQA databases (of different distortion scenarios) simultaneously. A key step in our approach is to create and combine image pairs within individual databases as the training set, which effectively bypasses the issue of perceptual scale realignment. We compute a continuous quality annotation for each pair from the corresponding human opinions, indicating the probability of one image having better perceptual quality. We train a deep neural network for BIQA over the training set of massive image pairs by minimizing the fidelity loss. Experiments on six IQA databases demonstrate that the optimized model by the proposed training strategy is effective in blindly assessing image quality in the laboratory and wild, outperforming previous BIQA methods by a large margin.