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.
@article{arxiv.2211.06769,
title = {Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report},
author = {Andrey Ignatov and Radu Timofte and Jin Zhang and Feng Zhang and Gaocheng Yu and Zhe Ma and Hongbin Wang and Minsu Kwon and Haotian Qian and Wentao Tong and Pan Mu and Ziping Wang and Guangjing Yan and Brian Lee and Lei Fei and Huaijin Chen and Hyebin Cho and Byeongjun Kwon and Munchurl Kim and Mingyang Qian and Huixin Ma and Yanan Li and Xiaotao Wang and Lei Lei},
journal= {arXiv preprint arXiv:2211.06769},
year = {2022}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2211.03885; text overlap with arXiv:2105.07809, arXiv:2211.04470, arXiv:2211.05256, arXiv:2211.05910