# Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report

arXiv: https://arxiv.org/abs/2211.03885 · HTML: https://mlsanity.com/paper/2211.03885/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 80 references that are in the map.
- First posted on arXiv 7 Nov 2022.

## Builds on (most cited first, 30 of 55)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [ZeroQ: A Novel Zero Shot Quantization Framework](https://mlsanity.com/paper/2001.00281/) (2020)
- [Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm](https://mlsanity.com/paper/1808.00278/) (2018)
- [MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning](https://mlsanity.com/paper/1903.10258/) (2019)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [Quantization Networks](https://mlsanity.com/paper/1911.09464/) (2019)
- [FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions](https://mlsanity.com/paper/2004.05565/) (2020)
- [Residual Feature Distillation Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2009.11551/) (2020)
- [Learning Accurate Dense Correspondences and When to Trust Them](https://mlsanity.com/paper/2101.01710/) (2021)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks](https://mlsanity.com/paper/1903.08066/) (2019)
- [ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting](https://mlsanity.com/paper/2007.03260/) (2020)
- [NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2005.01996/) (2020)
- [AI Benchmark: All About Deep Learning on Smartphones in 2019](https://mlsanity.com/paper/1910.06663/) (2019)
- [AI Benchmark: Running Deep Neural Networks on Android Smartphones](https://mlsanity.com/paper/1810.01109/) (2018)
- [Unsupervised Learning for Real-World Super-Resolution](https://mlsanity.com/paper/1909.09629/) (2019)

## Built on by (most cited first, 13 of 13)

- [NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results](https://mlsanity.com/paper/2505.12089/) (2025)
- [MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices](https://mlsanity.com/paper/2507.01838/) (2025)
- [SYENet: A Simple Yet Effective Network for Multiple Low-Level Vision Tasks with Real-time Performance on Mobile Device](https://mlsanity.com/paper/2308.08137/) (2023)
- [RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report](https://mlsanity.com/paper/2506.01947/) (2025)
- [Learned Lightweight Smartphone ISP with Unpaired Data](https://mlsanity.com/paper/2505.10420/) (2025)
- [PQDynamicISP: Dynamically Controlled Image Signal Processor for Any Image Sensors Pursuing Perceptual Quality](https://mlsanity.com/paper/2403.10091/) (2024)
- [Simple Image Signal Processing using Global Context Guidance](https://mlsanity.com/paper/2404.11569/) (2024)
- [Addressing Image Authenticity When Cameras Use Generative AI](https://mlsanity.com/paper/2604.21879/) (2026)
- [Realizing Unaligned Block-wise Pruning for DNN Acceleration on Mobile Devices](https://mlsanity.com/paper/2407.19644/) (2024)
- [Pushing Joint Image Denoising and Classification to the Edge](https://mlsanity.com/paper/2409.08943/) (2024)
- [Spatial-Frequency Aware for Object Detection in RAW Image](https://mlsanity.com/paper/2508.01396/) (2025)
- [LatentBurst: A Fast and Efficient Multi Frame Super-Resolution for Hexadeca-Bayer Pattern CIS images](https://mlsanity.com/paper/2604.23268/) (2026)
- [Benchmarking RAW and RGB Restoration in Image Signal Processors](https://mlsanity.com/paper/2609.02831/) (2026)

## Abstract (arXiv)

The role of mobile cameras increased dramatically over the past few years, leading to more and more research in automatic image quality enhancement and RAW photo processing. In this Mobile AI challenge, the target was to develop an efficient end-to-end AI-based image signal processing (ISP) pipeline replacing the standard mobile ISPs that can run on modern smartphone GPUs using TensorFlow Lite. The participants were provided with a large-scale Fujifilm UltraISP dataset consisting of thousands of paired photos captured with a normal mobile camera sensor and a professional 102MP medium-format FujiFilm GFX100 camera. The runtime of the resulting models was evaluated on the Snapdragon's 8 Gen 1 GPU that provides excellent acceleration results for the majority of common deep learning ops. The proposed solutions are compatible with all recent mobile GPUs, being able to process Full HD photos in less than 20-50 milliseconds while achieving high fidelity results. A detailed description of all models developed in this challenge is provided in this paper.