QMRNet: Quality Metric Regression for EO Image Quality Assessment and Super-Resolution
Not on the map. Why?
Abstract (arXiv)
Latest advances in Super-Resolution (SR) have been tested with general purpose images such as faces, landscapes and objects, mainly unused for the task of super-resolving Earth Observation (EO) images. In this research paper, we benchmark state-of-the-art SR algorithms for distinct EO datasets using both Full-Reference and No-Reference Image Quality Assessment (IQA) metrics. We also propose a novel Quality Metric Regression Network (QMRNet) that is able to predict quality (as a No-Reference metric) by training on any property of the image (i.e. its resolution, its distortions...) and also able to optimize SR algorithms for a specific metric objective. This work is part of the implementation of the framework IQUAFLOW which has been developed for evaluating image quality, detection and classification of objects as well as image compression in EO use cases. We integrated our experimentation and tested our QMRNet algorithm on predicting features like blur, sharpness, snr, rer and ground sampling distance (GSD) and obtain validation medRs below 1.0 (out of N=50) and recall rates above 95%. Overall benchmark shows promising results for LIIF, CAR and MSRN and also the potential use of QMRNet as Loss for optimizing SR predictions. Due to its simplicity, QMRNet could also be used for other use cases and image domains, as its architecture and data processing is fully scalable.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 55 references that are in the map. First posted on arXiv 12 Oct 2022.
Builds on
22 of 55 references.
References · 22
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2016Improved Techniques for Training GANscited by 2,970
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
- 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
- 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
- 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
- 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
- 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
- 2016Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessmentcited by 225
- 2019Generalized Sliced Wasserstein Distancescited by 208
- 2013Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Indexcited by 195
- 2018Recipe1M+: A Dataset for Learning Cross-Modal Embeddings for Cooking Recipes and Food Imagescited by 118
10 more
- 2018The Effects of Super-Resolution on Object Detection Performance in Satellite Imagerycited by 58
- 2016A Haar Wavelet-Based Perceptual Similarity Index for Image Quality Assessmentcited by 57
- 2019Learned Image Downscaling for Upscaling using Content Adaptive Resamplercited by 55
- 2018Cross-Modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddingscited by 35
- 2016Mean Deviation Similarity Index: Efficient and Reliable Full-Reference Image Quality Evaluatorcited by 32
- 2019ProxIQA: A Proxy Approach to Perceptual Optimization of Learned Image Compressioncited by 24
- 2022Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelitycited by 24
- 2017Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Networkcited by 17
- 2020Blind Quality Assessment for Image Superresolution Using Deep Two-Stream Convolutional Networkscited by 15
- 2020Super-resolution of multispectral satellite images using convolutional neural networkscited by 8
Built on by
Citing papers per year: 2023: 1.
1 paper.