mlsanityData to 14 Oct 2026

Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report

arXiv 2105.07825 ↗First posted 17 May 2021eess.IV cs.CV cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

Image super-resolution is one of the most popular computer vision problems with many important applications to mobile devices. While many solutions have been proposed for this task, they are usually not optimized even for common smartphone AI hardware, not to mention more constrained smart TV platforms that are often supporting INT8 inference only. To address this problem, we introduce the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based image super-resolution solutions that can demonstrate a real-time performance on mobile or edge NPUs. For this, the participants were provided with the DIV2K dataset and trained quantized models to do an efficient 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated NPU capable of accelerating quantized neural networks. The proposed solutions are fully compatible with all major mobile AI accelerators and are capable of reconstructing Full HD images under 40-60 ms while achieving high fidelity results. A detailed description of all models developed in the challenge is provided in this paper.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Builds on 31 of its 60 references that are in the map. First posted on arXiv 17 May 2021.

Builds on

31 of 60 references.

References · 31

  1. 2019Searching for MobileNetV3cited by 1,994
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
  3. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  4. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  5. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  6. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 903
  7. 2021RepVGG: Making VGG-style ConvNets Great Againcited by 522
  8. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  9. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 269
  10. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 235
  11. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 227
  12. 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
19 more
  1. 2019Quantization Networkscited by 153
  2. 2020FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensionscited by 152
  3. 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
  4. 2019Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networkscited by 90
  5. 2020NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 83
  6. 2019AI Benchmark: All About Deep Learning on Smartphones in 2019cited by 77
  7. 2018AI Benchmark: Running Deep Neural Networks on Android Smartphonescited by 75
  8. 2019Learning Filter Basis for Convolutional Neural Network Compressioncited by 57
  9. 2020Rendering Natural Camera Bokeh Effect with Deep Learningcited by 57
  10. 2015Seven ways to improve example-based single image super resolutioncited by 51
  11. 2020NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Resultscited by 51
  12. 2020AIM 2020 Challenge on Learned Image Signal Processing Pipelinecited by 44
  13. 2018PIRM Challenge on Perceptual Image Enhancement on Smartphones: Reportcited by 38
  14. 2017WESPE: Weakly Supervised Photo Enhancer for Digital Camerascited by 32
  15. 2020AIM 2020 Challenge on Rendering Realistic Bokehcited by 26
  16. 2020T-Basis: a Compact Representation for Neural Networkscited by 21
  17. 2020NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Resultscited by 19
  18. 2020Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latencycited by 16
  19. 2020Controlling Information Capacity of Binary Neural Networkcited by 15

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 18; 2023: 9; 2024: 3; 2025: 1.

34 papers.

Sort:

By area:

  1. 2022Residual Local Feature Network for Efficient Super-Resolutioncited by 53
  2. 2023NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancementcited by 31
  3. 2021Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devicescited by 30
  4. 2022CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolutioncited by 27
  5. 2022FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsamplingcited by 25
  6. 2021Anchor-based Plain Net for Mobile Image Super-Resolutioncited by 24
  7. 2024See More Details: Efficient Image Super-Resolution by Experts Miningcited by 23
  8. 2022Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolutioncited by 20
  9. 2023DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolutioncited by 19
  10. 2023Low-field magnetic resonance image enhancement via stochastic image quality transfercited by 19
  11. 2024Real-Time 4K Super-Resolution of Compressed AVIF Images. AIS 2024 Challenge Surveycited by 19
  12. 2022Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Reportcited by 16
22 more
  1. 2022Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Reportcited by 13
  2. 2022MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learningcited by 13
  3. 2021edge-SR: Super-Resolution For The Massescited by 9
  4. 2022CUF: Continuous Upsampling Filterscited by 8
  5. 2023AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutionscited by 8
  6. 2022PyNet-V2 Mobile: Efficient On-Device Photo Processing With Neural Networkscited by 7
  7. 2022Fast Nearest Convolution for Real-Time Efficient Image Super-Resolutioncited by 6
  8. 2023Bicubic++: Slim, Slimmer, Slimmest -- Designing an Industry-Grade Super-Resolution Networkcited by 6
  9. 2023Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networkscited by 5
  10. 2023SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Devicecited by 5
  11. 2022QuantNAS for super resolution: searching for efficient quantization-friendly architectures against quantization noisecited by 4
  12. 2022Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Reportcited by 4
  13. 2023Data Upcycling Knowledge Distillation for Image Super-Resolutioncited by 4
  14. 2022Sliding Window Recurrent Network for Efficient Video Super-Resolutioncited by 3
  15. 2022XCAT -- Lightweight Quantized Single Image Super-Resolution using Heterogeneous Group Convolutions and Cross Concatenationcited by 3
  16. 2022Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Reportcited by 3
  17. 2024FADE: A Task-Agnostic Upsampling Operator for Encoder-Decoder Architecturescited by 3
  18. 2022Real-Time Super-Resolution for Real-World Images on Mobile Devicescited by 2
  19. 2022Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Reportcited by 2
  20. 2022NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolutioncited by 1
  21. 2023Towards Clip-Free Quantized Super-Resolution Networks: How to Tame Representative Imagescited by 0
  22. 2025Compressed Domain Prior-Guided Video Super-Resolution for Cloud Gaming Contentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms
  2. 2021Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Report
  3. 2022Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
  4. 2022Generative Adversarial Super-Resolution at the Edge with Knowledge Distillation
  5. 2026QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks
  6. 2026Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUs
  7. 2021Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
  8. 2024AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution