# Assessing Image Quality Issues for Real-World Problems

arXiv: https://arxiv.org/abs/2003.12511 · HTML: https://mlsanity.com/paper/2003.12511/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2020.

## Built on by (most cited first, 28 of 28)

- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [MultiInstruct: Improving Multi-Modal Zero-Shot Learning via Instruction Tuning](https://mlsanity.com/paper/2212.10773/) (2022)
- [Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly](https://mlsanity.com/paper/2204.13631/) (2022)
- [ARNIQA: Learning Distortion Manifold for Image Quality Assessment](https://mlsanity.com/paper/2310.14918/) (2023)
- [Grounding Answers for Visual Questions Asked by Visually Impaired People](https://mlsanity.com/paper/2202.01993/) (2022)
- [Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment](https://mlsanity.com/paper/2403.11176/) (2024)
- [DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild](https://mlsanity.com/paper/2405.19996/) (2024)
- [VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments](https://mlsanity.com/paper/2207.11810/) (2022)
- [Right this way: Can VLMs Guide Us to See More to Answer Questions?](https://mlsanity.com/paper/2411.00394/) (2024)
- [Quality-agnostic Image Captioning to Safely Assist People with Vision Impairment](https://mlsanity.com/paper/2304.14623/) (2023)
- [Salient Object Detection for Images Taken by People With Vision Impairments](https://mlsanity.com/paper/2301.05323/) (2023)
- [Explaining CLIP's performance disparities on data from blind/low vision users](https://mlsanity.com/paper/2311.17315/) (2023)
- [Anomaly Detection for People with Visual Impairments Using an Egocentric 360-Degree Camera](https://mlsanity.com/paper/2411.10945/) (2024)
- [Using Semantic Information for Defining and Detecting OOD Inputs](https://mlsanity.com/paper/2302.11019/) (2023)
- [Empowering Visually Impaired Individuals: A Novel Use of Apple Live Photos and Android Motion Photos](https://mlsanity.com/paper/2309.08022/) (2023)
- [BIV-Priv-Seg: Locating Private Content in Images Taken by People With Visual Impairments](https://mlsanity.com/paper/2407.18243/) (2024)
- [Understanding How Blind Users Handle Object Recognition Errors: Strategies and Challenges](https://mlsanity.com/paper/2408.03303/) (2024)
- [Blind VQA on 360deg Video via Progressively Learning from Pixels, Frames and Video](https://mlsanity.com/paper/2111.09503/) (2021)
- ["It's trained by non-disabled people": Evaluating How Image Quality Affects Product Captioning with Vision-Language Models](https://mlsanity.com/paper/2511.08917/) (2025)
- [Helping Visually Impaired People Take Better Quality Pictures](https://mlsanity.com/paper/2305.08066/) (2023)
- [ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models](https://mlsanity.com/paper/2603.19466/) (2026)
- [Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics](https://mlsanity.com/paper/2407.06450/) (2024)
- [EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering](https://mlsanity.com/paper/2206.14355/) (2022)
- [Feedback is Needed for Retakes: An Explainable Poor Image Notification Framework for the Visually Impaired](https://mlsanity.com/paper/2211.09427/) (2022)
- [Extreme Amodal Face Detection](https://mlsanity.com/paper/2510.06791/) (2025)
- [Hierarchical Instance Tracking to Balance Privacy Preservation with Accessible Information](https://mlsanity.com/paper/2512.10102/) (2025)
- [SHAMISA: SHAped Modeling of Implicit Structural Associations for Self-supervised No-Reference Image Quality Assessment](https://mlsanity.com/paper/2603.13669/) (2026)

## Abstract (arXiv)

We introduce a new large-scale dataset that links the assessment of image quality issues to two practical vision tasks: image captioning and visual question answering. First, we identify for 39,181 images taken by people who are blind whether each is sufficient quality to recognize the content as well as what quality flaws are observed from six options. These labels serve as a critical foundation for us to make the following contributions: (1) a new problem and algorithms for deciding whether an image is insufficient quality to recognize the content and so not captionable, (2) a new problem and algorithms for deciding which of six quality flaws an image contains, (3) a new problem and algorithms for deciding whether a visual question is unanswerable due to unrecognizable content versus the content of interest being missing from the field of view, and (4) a novel application of more efficiently creating a large-scale image captioning dataset by automatically deciding whether an image is insufficient quality and so should not be captioned. We publicly-share our datasets and code to facilitate future extensions of this work: https://vizwiz.org.