mlsanityData to 7 Oct 2026

Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report

arXiv 2105.08629 ↗First posted 17 May 2021eess.IV cs.CV cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Image denoising is one of the most critical problems in mobile photo processing. While many solutions have been proposed for this task, they are usually working with synthetic data and are too computationally expensive to run on mobile devices. 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 denoising solution that can demonstrate high efficiency on smartphone GPUs. For this, the participants were provided with a novel large-scale dataset consisting of noisy-clean image pairs captured in the wild. The runtime of all models was evaluated on the Samsung Exynos 2100 chipset with a powerful Mali GPU capable of accelerating floating-point and quantized neural networks. The proposed solutions are fully compatible with any mobile GPU and are capable of processing 480p resolution images under 40-80 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 15 papers in the map (data through 7 Oct 2026). Builds on 38 of its 62 references that are in the map. First posted on arXiv 17 May 2021.

Builds on

38 of 62 references.

References · 38

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2019Searching for MobileNetV3cited by 1,984
  6. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  7. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  8. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  9. 2021Multi-Stage Progressive Image Restorationcited by 813
  10. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  11. 2015Cyclical Learning Rates for Training Neural Networkscited by 627
  12. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
26 more
  1. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  2. 2019A Comprehensive Overhaul of Feature Distillationcited by 341
  3. 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 265
  4. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  5. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
  6. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  7. 2019ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blockscited by 178
  8. 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
  9. 2020FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensionscited by 152
  10. 2019Quantization Networkscited by 151
  11. 2020Replacing Mobile Camera ISP with a Single Deep Learning Modelcited by 108
  12. 2019Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networkscited by 87
  13. 2020NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 83
  14. 2019AI Benchmark: All About Deep Learning on Smartphones in 2019cited by 76
  15. 2018AI Benchmark: Running Deep Neural Networks on Android Smartphonescited by 75
  16. 2019Learning Filter Basis for Convolutional Neural Network Compressioncited by 57
  17. 2020Rendering Natural Camera Bokeh Effect with Deep Learningcited by 57
  18. 2020NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Resultscited by 51
  19. 2020AIM 2020 Challenge on Learned Image Signal Processing Pipelinecited by 44
  20. 2018PIRM Challenge on Perceptual Image Enhancement on Smartphones: Reportcited by 38
  21. 2019Efficient Residual Dense Block Search for Image Super-Resolutioncited by 37
  22. 2017WESPE: Weakly Supervised Photo Enhancer for Digital Camerascited by 32
  23. 2020AIM 2020 Challenge on Rendering Realistic Bokehcited by 26
  24. 2020T-Basis: a Compact Representation for Neural Networkscited by 21
  25. 2020Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latencycited by 16
  26. 2020Controlling Information Capacity of Binary Neural Networkcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 2; 2024: 1; 2025: 0; 2026: 4.

15 papers.

Sort:

  1. 2023Image Denoising: The Deep Learning Revolution and Beyond -- A Survey Paper --cited by 71
  2. 2022Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Reportcited by 16
  3. 2022Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Reportcited by 13
  4. 2022MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learningcited by 13
  5. 2022PyNet-V2 Mobile: Efficient On-Device Photo Processing With Neural Networkscited by 7
  6. 2022LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNNcited by 6
  7. 2022Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Reportcited by 4
  8. 2022Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Reportcited by 3
  9. 2022Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Reportcited by 2
  10. 2026Real Image Denoising with Knowledge Distillation for High-Performance Mobile NPUscited by 2
  11. 2026Diffusion-Based sRGB Real Noise Generation via Prompt-Driven Noise Representation Learningcited by 1
  12. 2023The Two Faces of AI in Green Mobile Computing: A Literature Reviewcited by 0
3 more
  1. 2024Realizing Unaligned Block-wise Pruning for DNN Acceleration on Mobile Devicescited by 0
  2. 2026FastSHADE: Fast Self-augmented Hierarchical Asymmetric Denoising for Efficient inference on mobile devicescited by 0
  3. 2026YeTI: You Only Need Two Noisy Images for Real-World sRGB Noise Generationcited by 0