mlsanityData to 14 Oct 2026

SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning

arXiv 2306.14070 ↗First posted 24 Jun 2023cs.CV eess.IV physics.comp-phcited by 18

Not on the map. Why?

Abstract (arXiv)

Super-resolution (SR) techniques aim to enhance data resolution, enabling the retrieval of finer details, and improving the overall quality and fidelity of the data representation. There is growing interest in applying SR methods to complex spatiotemporal systems within the Scientific Machine Learning (SciML) community, with the hope of accelerating numerical simulations and/or improving forecasts in weather, climate, and related areas. However, the lack of standardized benchmark datasets for comparing and validating SR methods hinders progress and adoption in SciML. To address this, we introduce SuperBench, the first benchmark dataset featuring high-resolution datasets, including data from fluid flows, cosmology, and weather. Here, we focus on validating spatial SR performance from data-centric and physics-preserved perspectives, as well as assessing robustness to data degradation tasks. While deep learning-based SR methods (developed in the computer vision community) excel on certain tasks, despite relatively limited prior physics information, we identify limitations of these methods in accurately capturing intricate fine-scale features and preserving fundamental physical properties and constraints in scientific data. These shortcomings highlight the importance and subtlety of incorporating domain knowledge into ML models. We anticipate that SuperBench will help to advance SR methods for science.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 43 of its 97 references that are in the map. First posted on arXiv 24 Jun 2023.

Builds on

43 of 97 references.

References · 43

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  6. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  7. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  8. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  9. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  10. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  11. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  12. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
31 more
  1. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  2. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  3. 2020Pre-Trained Image Processing Transformercited by 893
  4. 2018Residual Dense Network for Image Super-Resolutioncited by 799
  5. 2021Characterizing possible failure modes in physics-informed neural networkscited by 643
  6. 2019DeepXDE: A deep learning library for solving differential equationscited by 619
  7. 2022PDEBENCH: An Extensive Benchmark for Scientific Machine Learningcited by 413
  8. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 403
  9. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 394
  10. 2019Deep Learning for Image Super-resolution: A Surveycited by 369
  11. 2020Learning Texture Transformer Network for Image Super-Resolutioncited by 347
  12. 2020WeatherBench: A benchmark dataset for data-driven weather forecastingcited by 275
  13. 2019Towards Physics-informed Deep Learning for Turbulent Flow Predictioncited by 204
  14. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  15. 2022A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstructioncited by 152
  16. 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
  17. 2021Enhancing Computational Fluid Dynamics with Machine Learningcited by 138
  18. 2019A Deep Journey into Super-resolution: A surveycited by 86
  19. 2020MeshfreeFlowNet: A Physics-Constrained Deep Continuous Space-Time Super-Resolution Frameworkcited by 78
  20. 2018Wide Activation for Efficient and Accurate Image Super-Resolutioncited by 65
  21. 2019Unsupervised Learning for Real-World Super-Resolutioncited by 64
  22. 2021Scientific Machine Learning Benchmarkscited by 60
  23. 2021Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learningcited by 57
  24. 2021SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learningcited by 54
  25. 2022Learning differentiable solvers for systems with hard constraintscited by 34
  26. 2023Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flowscited by 31
  27. 2022Learning continuous models for continuous physicscited by 28
  28. 2022Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advancescited by 22
  29. 2020Turbulence Enrichment using Physics-informed Generative Adversarial Networkscited by 18
  30. 2020Physics-Informed Neural Network Super Resolution for Advection-Diffusion Modelscited by 16
  31. 2022Physics-informed Deep Super-resolution for Spatiotemporal Datacited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 5; 2025: 9; 2026: 2.

18 papers.

Sort:

By area:

  1. 2023Neural Operators for Accelerating Scientific Simulations and Designcited by 221
  2. 2025SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Paperscited by 43
  3. 2024Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learningcited by 32
  4. 2023BubbleML: A Multi-Physics Dataset and Benchmarks for Machine Learningcited by 17
  5. 2024MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modelingcited by 12
  6. 2024Hierarchical Neural Operator Transformer with Learnable Frequency-aware Loss Prior for Arbitrary-scale Super-resolutioncited by 11
  7. 2025FLEX: A Backbone for Diffusion-Based Modeling of Spatio-temporal Physical Systemscited by 8
  8. 2025The False Promise of Zero-Shot Super-Resolution in Machine-Learned Operatorscited by 8
  9. 2024Observation-Guided Meteorological Field Downscaling at Station Scale: A Benchmark and a New Methodcited by 7
  10. 2025Exploring Scalable Unified Modeling for General Low-Level Visioncited by 4
  11. 2025PC-SRGAN: Physically Consistent Super-Resolution Generative Adversarial Network for General Transient Simulationscited by 2
  12. 2026Iterative Refinement Neural Operators are Learned Fixed-Point Solvers: A Principled Approach to Spectral Bias Mitigationcited by 2
6 more
  1. 2024ConDiff: A Challenging Dataset for Neural Solvers of Partial Differential Equationscited by 1
  2. 2025SERA-H: Super-Resolution of Sentinel Time Series for Fine-Scale Canopy Height Mappingcited by 1
  3. 20264KLSDB: A Large-Scale Dataset for 4K Image Restoration and Generationcited by 1
  4. 2025Embedding Trust at Scale: Physics-Aware Neural Watermarking for Secure and Verifiable Data Pipelinescited by 0
  5. 2025Downscaling climate projections to 1 km with single-image super resolutioncited by 0
  6. 2025Dynamical Implicit Neural Representationscited by 0