mlsanityData to 7 Oct 2026

Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report

arXiv 2211.05910 ↗First posted 7 Nov 2022eess.IV cs.CVcited by 16

Not on the map. Why?

Abstract (arXiv)

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints. In this Mobile AI challenge, we address this problem and propose the participants to design an efficient quantized image super-resolution solution that can demonstrate a real-time performance on mobile NPUs. The participants were provided with the DIV2K dataset and trained INT8 models to do a high-quality 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU capable of accelerating quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 60 FPS rate when reconstructing Full HD resolution images. A detailed description of all models developed in the challenge is provided in this paper.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 57 of its 95 references that are in the map. First posted on arXiv 7 Nov 2022.

Builds on

57 of 95 references.

References · 57

  1. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  2. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  3. 2019Searching for MobileNetV3cited by 1,984
  4. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  6. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  7. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  8. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  9. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 520
  10. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  11. 2020AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradientscited by 282
  12. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
38 more
  1. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  2. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  3. 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
  4. 2020FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensionscited by 152
  5. 2019Quantization Networkscited by 151
  6. 2015Structured Pruning of Deep Convolutional Neural Networkscited by 148
  7. 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
  8. 2019Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networkscited by 87
  9. 2021Diverse Branch Block: Building a Convolution as an Inception-like Unitcited by 87
  10. 2020NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 83
  11. 2019AI Benchmark: All About Deep Learning on Smartphones in 2019cited by 76
  12. 2018AI Benchmark: Running Deep Neural Networks on Android Smartphonescited by 75
  13. 2019Learning Filter Basis for Convolutional Neural Network Compressioncited by 57
  14. 2020Rendering Natural Camera Bokeh Effect with Deep Learningcited by 57
  15. 2022Residual Local Feature Network for Efficient Super-Resolutioncited by 53
  16. 2015Seven ways to improve example-based single image super resolutioncited by 51
  17. 2020NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Resultscited by 51
  18. 2017DiracNets: Training Very Deep Neural Networks Without Skip-Connectionscited by 47
  19. 2020AIM 2020 Challenge on Learned Image Signal Processing Pipelinecited by 44
  20. 2022NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Resultscited by 40
  21. 2018PIRM Challenge on Perceptual Image Enhancement on Smartphones: Reportcited by 38
  22. 2021Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 34
  23. 2021Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Reportcited by 34
  24. 2017WESPE: Weakly Supervised Photo Enhancer for Digital Camerascited by 32
  25. 2021Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devicescited by 30
  26. 2022Fast and Memory-Efficient Network Towards Efficient Image Super-Resolutioncited by 27
  27. 2020AIM 2020 Challenge on Rendering Realistic Bokehcited by 26
  28. 2021Anchor-based Plain Net for Mobile Image Super-Resolutioncited by 24
  29. 2021Towards Compact Single Image Super-Resolution via Contrastive Self-distillationcited by 24
  30. 2020T-Basis: a Compact Representation for Neural Networkscited by 21
  31. 2022AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Resultscited by 20
  32. 2021Collapsible Linear Blocks for Super-Efficient Super Resolutioncited by 19
  33. 2021Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Reportcited by 19
  34. 2021Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 19
  35. 2020NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Resultscited by 18
  36. 2020Fully Quantized Image Super-Resolution Networkscited by 18
  37. 2020Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latencycited by 16
  38. 2020Controlling Information Capacity of Binary Neural Networkcited by 15

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 4; 2025: 2; 2026: 3.

16 papers.

Sort:

By area:

  1. 2023Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolutioncited by 56
  2. 2024See More Details: Efficient Image Super-Resolution by Experts Miningcited by 23
  3. 2022Make RepVGG Greater Again: A Quantization-aware Approachcited by 21
  4. 2023DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolutioncited by 19
  5. 2024Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Surveycited by 19
  6. 2024SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolutioncited by 10
  7. 2023AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutionscited by 8
  8. 2023Bicubic++: Slim, Slimmer, Slimmest -- Designing an Industry-Grade Super-Resolution Networkcited by 6
  9. 2023QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platformscited by 4
  10. 2025SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioningcited by 3
  11. 2024LMLT: Low-to-high Multi-Level Vision Transformer for Image Super-Resolutioncited by 1
  12. 2026Addressing Image Authenticity When Cameras Use Generative AIcited by 1
4 more
  1. 2023Towards Clip-Free Quantized Super-Resolution Networks: How to Tame Representative Imagescited by 0
  2. 2025Compressed Domain Prior-Guided Video Super-Resolution for Cloud Gaming Contentcited by 0
  3. 2026Efficient INT8 Single-Image Super-Resolution via Deployment-Aware Quantization and Teacher-Guided Trainingcited by 0
  4. 2026QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networkscited by 0