AIM 2020 Challenge on Rendering Realistic Bokeh

Abstract

This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world bokeh simulation problem, where the goal was to learn a realistic shallow focus technique using a large-scale EBB! bokeh dataset consisting of 5K shallow / wide depth-of-field image pairs captured using the Canon 7D DSLR camera. The participants had to render bokeh effect based on only one single frame without any additional data from other cameras or sensors. The target metric used in this challenge combined the runtime and the perceptual quality of the solutions measured in the user study. To ensure the efficiency of the submitted models, we measured their runtime on standard desktop CPUs as well as were running the models on smartphone GPUs. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical bokeh effect rendering problem.

Cite

Text

Ignatov et al. "AIM 2020 Challenge on Rendering Realistic Bokeh." European Conference on Computer Vision Workshops, 2020. doi:10.1007/978-3-030-67070-2_13

Markdown

[Ignatov et al. "AIM 2020 Challenge on Rendering Realistic Bokeh." European Conference on Computer Vision Workshops, 2020.](https://mlanthology.org/eccvw/2020/ignatov2020eccvw-aim/) doi:10.1007/978-3-030-67070-2_13

BibTeX

@inproceedings{ignatov2020eccvw-aim,
  title     = {{AIM 2020 Challenge on Rendering Realistic Bokeh}},
  author    = {Ignatov, Andrey and Timofte, Radu and Qian, Ming and Qiao, Congyu and Lin, Jiamin and Guo, Zhenyu and Li, Chenghua and Leng, Cong and Cheng, Jian and Peng, Juewen and Luo, Xianrui and Xian, Ke and Wu, Zijin and Cao, Zhiguo and Puthussery, Densen and Jiji, C. V. and Hrishikesh, P. S and Kuriakose, Melvin and Dutta, Saikat and Das, Sourya Dipta and Shah, Nisarg A. and Purohit, Kuldeep and Kandula, Praveen and Suin, Maitreya and Rajagopalan, A. N. and Saagara, M. B and Minnu, A. L and Sanjana, A. R and S, Praseeda and Wu, Ge and Chen, Xueqin and Wang, Tengyao and Zheng, Max and Wong, Hulk and Zou, Jay},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2020},
  pages     = {213-228},
  doi       = {10.1007/978-3-030-67070-2_13},
  url       = {https://mlanthology.org/eccvw/2020/ignatov2020eccvw-aim/}
}