# Image Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness

arXiv: https://arxiv.org/abs/2105.07139 · HTML: https://mlsanity.com/paper/2105.07139/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 32 references that are in the map.
- First posted on arXiv 15 May 2021.

## Builds on (most cited first, 9 of 9)

- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network](https://mlsanity.com/paper/1707.05425/) (2017)
- [Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networks](https://mlsanity.com/paper/2004.06163/) (2020)
- [Encoding Visual Sensitivity by MaxPol Convolution Filters for Image Sharpness Assessment](https://mlsanity.com/paper/1808.00617/) (2018)

## Built on by (most cited first, 15 of 15)

- [Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity](https://mlsanity.com/paper/2207.08689/) (2022)
- [ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution](https://mlsanity.com/paper/2110.09992/) (2021)
- [Deep Neural Network for Blind Visual Quality Assessment of 4K Content](https://mlsanity.com/paper/2206.04363/) (2022)
- [MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusion](https://mlsanity.com/paper/2205.10101/) (2022)
- [A No-Reference Deep Learning Quality Assessment Method for Super-resolution Images Based on Frequency Maps](https://mlsanity.com/paper/2206.04289/) (2022)
- [Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metric](https://mlsanity.com/paper/2203.08923/) (2022)
- [Dehazed Image Quality Evaluation: From Partial Discrepancy to Blind Perception](https://mlsanity.com/paper/2211.12636/) (2022)
- [VQualA 2025 Challenge on Image Super-Resolution Generated Content Quality Assessment: Methods and Results](https://mlsanity.com/paper/2509.06413/) (2025)
- [Alternative Learning Paradigms for Image Quality Transfer](https://mlsanity.com/paper/2411.05885/) (2024)
- [SPQE: Structure-and-Perception-Based Quality Evaluation for Image Super-Resolution](https://mlsanity.com/paper/2205.03584/) (2022)
- [Perception-oriented Bidirectional Attention Network for Image Super-resolution Quality Assessment](https://mlsanity.com/paper/2509.06442/) (2025)
- [Exploring the Effect of Sparse Recovery on the Quality of Image Superresolution](https://mlsanity.com/paper/2308.02714/) (2023)
- [Textural-Perceptual Joint Learning for No-Reference Super-Resolution Image Quality Assessment](https://mlsanity.com/paper/2205.13847/) (2022)
- [Structure Modeling Activation Free Fourier Network for Spacecraft Image Denoising](https://mlsanity.com/paper/2409.07067/) (2024)
- [Perceptual Quality Optimization of Image Super-Resolution](https://mlsanity.com/paper/2602.21482/) (2026)

## Abstract (arXiv)

Single image super-resolution (SISR) algorithms reconstruct high-resolution (HR) images with their low-resolution (LR) counterparts. It is desirable to develop image quality assessment (IQA) methods that can not only evaluate and compare SISR algorithms, but also guide their future development. In this paper, we assess the quality of SISR generated images in a two-dimensional (2D) space of structural fidelity versus statistical naturalness. This allows us to observe the behaviors of different SISR algorithms as a tradeoff in the 2D space. Specifically, SISR methods are traditionally designed to achieve high structural fidelity but often sacrifice statistical naturalness, while recent generative adversarial network (GAN) based algorithms tend to create more natural-looking results but lose significantly on structural fidelity. Furthermore, such a 2D evaluation can be easily fused to a scalar quality prediction. Interestingly, we find that a simple linear combination of a straightforward local structural fidelity and a global statistical naturalness measures produce surprisingly accurate predictions of SISR image quality when tested using public subject-rated SISR image datasets. Code of the proposed SFSN model is publicly available at urlhttps://github.com/weizhou-geek/SFSN.