Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 Challenge: Report
Abstract
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.
Cite
Text
Ignatov et al. "Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 Challenge: Report." European Conference on Computer Vision Workshops, 2022. doi:10.1007/978-3-031-25066-8_7Markdown
[Ignatov et al. "Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 Challenge: Report." European Conference on Computer Vision Workshops, 2022.](https://mlanthology.org/eccvw/2022/ignatov2022eccvw-realistic/) doi:10.1007/978-3-031-25066-8_7BibTeX
@inproceedings{ignatov2022eccvw-realistic,
title = {{Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 Challenge: Report}},
author = {Ignatov, Andrey and Timofte, Radu and Zhang, Jin and Zhang, Feng and Yu, Gaocheng and Ma, Zhe and Wang, Hongbin and Kwon, Minsu and Qian, Haotian and Tong, Wentao and Mu, Pan and Wang, Ziping and Yan, Guangjing and Lee, Brian and Fei, Lei and Chen, Huaijin G. and Cho, Hyebin and Kwon, Byeongjun and Kim, Munchurl and Qian, Mingyang and Ma, Huixin and Li, Yanan and Wang, Xiaotao and Lei, Lei},
booktitle = {European Conference on Computer Vision Workshops},
year = {2022},
pages = {153-173},
doi = {10.1007/978-3-031-25066-8_7},
url = {https://mlanthology.org/eccvw/2022/ignatov2022eccvw-realistic/}
}