Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report
Not on the map. Why?
Abstract (arXiv)
As mobile cameras with compact optics are unable to produce a strong bokeh effect, lots of interest is now devoted to deep learning-based solutions for this task. In this Mobile AI challenge, the target was to develop an efficient end-to-end AI-based bokeh effect rendering approach that can run on modern smartphone GPUs using TensorFlow Lite. The participants were provided with a large-scale EBB! bokeh dataset consisting of 5K shallow / wide depth-of-field image pairs captured using the Canon 7D DSLR camera. The runtime of the resulting models was evaluated on the Kirin 9000's Mali GPU that provides excellent acceleration results for the majority of common deep learning ops. A detailed description of all models developed in this challenge is provided in this paper.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 48 of its 75 references that are in the map. First posted on arXiv 7 Nov 2022.
Builds on
48 of 75 references.
References · 48
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
- 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
- 2019Searching for MobileNetV3cited by 1,994
- 2021Vision Transformers for Dense Predictioncited by 1,803
- 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,593
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
- 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
- 2022Simple Baselines for Image Restorationcited by 708
- 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
36 more
- 2020ZeroQ: A Novel Zero Shot Quantization Frameworkcited by 269
- 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 235
- 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 227
- 2022Separable Self-attention for Mobile Vision Transformerscited by 163
- 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
- 2019Quantization Networkscited by 153
- 2020FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensionscited by 152
- 2019Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networkscited by 90
- 2020NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Resultscited by 83
- 2019AI Benchmark: All About Deep Learning on Smartphones in 2019cited by 77
- 2018AI Benchmark: Running Deep Neural Networks on Android Smartphonescited by 75
- 2020HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histogramscited by 64
- 2019Learning Filter Basis for Convolutional Neural Network Compressioncited by 57
- 2020Rendering Natural Camera Bokeh Effect with Deep Learningcited by 57
- 2022BokehMe: When Neural Rendering Meets Classical Renderingcited by 48
- 2020AIM 2020 Challenge on Learned Image Signal Processing Pipelinecited by 44
- 2018PIRM Challenge on Perceptual Image Enhancement on Smartphones: Reportcited by 38
- 2021Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 34
- 2021Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Reportcited by 34
- 2019On-Device Neural Net Inference with Mobile GPUscited by 32
- 2017Fast Deep Matting for Portrait Animation on Mobile Phonecited by 30
- 2020AIM 2020 Challenge on Rendering Realistic Bokehcited by 26
- 2020T-Basis: a Compact Representation for Neural Networkscited by 21
- 2022AIM 2022 Challenge on Super-Resolution of Compressed Image and Video: Dataset, Methods and Resultscited by 20
- 2020BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokehcited by 19
- 2021Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Reportcited by 19
- 2021Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 19
- 2021Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Imagecited by 18
- 2020Deploying Image Deblurring across Mobile Devices: A Perspective of Quality and Latencycited by 16
- 2020Controlling Information Capacity of Binary Neural Networkcited by 15
- 2021Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Reportcited by 15
- 2022Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Reportcited by 11
- 2020Depth-aware Blending of Smoothed Images for Bokeh Effect Generationcited by 10
- 2021Fast and Accurate Quantized Camera Scene Detection on Smartphones, Mobile AI 2021 Challenge: Reportcited by 10
- 2022AIM 2022 Challenge on Instagram Filter Removal: Methods and Resultscited by 6
- 2022Bokeh-Loss GAN: Multi-Stage Adversarial Training for Realistic Edge-Aware Bokehcited by 3
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.