# KonX: Cross-Resolution Image Quality Assessment

arXiv: https://arxiv.org/abs/2212.05813 · HTML: https://mlsanity.com/paper/2212.05813/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 65 references that are in the map.
- First posted on arXiv 12 Dec 2022.

## Builds on (most cited first, 20 of 20)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [YFCC100M: The New Data in Multimedia Research](https://mlsanity.com/paper/1503.01817/) (2015)
- [From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality](https://mlsanity.com/paper/1912.10088/) (2019)
- [Fixing the train-test resolution discrepancy](https://mlsanity.com/paper/1906.06423/) (2019)
- [No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency](https://mlsanity.com/paper/2108.06858/) (2021)
- [MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2004.05508/) (2020)
- [Transformer for Image Quality Assessment](https://mlsanity.com/paper/2101.01097/) (2020)
- [Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessment](https://mlsanity.com/paper/2008.03889/) (2020)
- [Effective Aesthetics Prediction with Multi-level Spatially Pooled Features](https://mlsanity.com/paper/1904.01382/) (2019)
- [Fixing the train-test resolution discrepancy: FixEfficientNet](https://mlsanity.com/paper/2003.08237/) (2020)
- [DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning](https://mlsanity.com/paper/2001.08113/) (2020)
- [Blind Predicting Similar Quality Map for Image Quality Assessment](https://mlsanity.com/paper/1805.08493/) (2018)
- [Learning scale-variant and scale-invariant features for deep image classification](https://mlsanity.com/paper/1602.01255/) (2016)
- [Crowd Counting by Adaptively Fusing Predictions from an Image Pyramid](https://mlsanity.com/paper/1805.06115/) (2018)
- [PerSIM: Multi-resolution Image Quality Assessment in the Perceptually Uniform Color Domain](https://mlsanity.com/paper/1811.07417/) (2018)

## Built on by (most cited first, 9 of 9)

- [UHD-IQA Benchmark Database: Pushing the Boundaries of Blind Photo Quality Assessment](https://mlsanity.com/paper/2406.17472/) (2024)
- [Assessing UHD Image Quality from Aesthetics, Distortions, and Saliency](https://mlsanity.com/paper/2409.00749/) (2024)
- [High Resolution Image Quality Database](https://mlsanity.com/paper/2401.16087/) (2024)
- [LAR-IQA: A Lightweight, Accurate, and Robust No-Reference Image Quality Assessment Model](https://mlsanity.com/paper/2408.17057/) (2024)
- [AIM 2024 Challenge on UHD Blind Photo Quality Assessment](https://mlsanity.com/paper/2409.16271/) (2024)
- [Charm: The Missing Piece in ViT fine-tuning for Image Aesthetic Assessment](https://mlsanity.com/paper/2504.02522/) (2025)
- [Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution](https://mlsanity.com/paper/2502.06476/) (2025)
- [MobileIQA: Exploiting Mobile-level Diverse Opinion Network For No-Reference Image Quality Assessment Using Knowledge Distillation](https://mlsanity.com/paper/2409.01212/) (2024)
- [Subjective and Objective Quality Evaluation of Super-Resolution Enhanced Broadcast Images on a Novel SR-IQA Dataset](https://mlsanity.com/paper/2409.17451/) (2024)

## Abstract (arXiv)

Scale-invariance is an open problem in many computer vision subfields. For example, object labels should remain constant across scales, yet model predictions diverge in many cases. This problem gets harder for tasks where the ground-truth labels change with the presentation scale. In image quality assessment (IQA), downsampling attenuates impairments, e.g., blurs or compression artifacts, which can positively affect the impression evoked in subjective studies. To accurately predict perceptual image quality, cross-resolution IQA methods must therefore account for resolution-dependent errors induced by model inadequacies as well as for the perceptual label shifts in the ground truth. We present the first study of its kind that disentangles and examines the two issues separately via KonX, a novel, carefully crafted cross-resolution IQA database. This paper contributes the following: 1. Through KonX, we provide empirical evidence of label shifts caused by changes in the presentation resolution. 2. We show that objective IQA methods have a scale bias, which reduces their predictive performance. 3. We propose a multi-scale and multi-column DNN architecture that improves performance over previous state-of-the-art IQA models for this task, including recent transformers. We thus both raise and address a novel research problem in image quality assessment.