ML Anthology

AIM 2019 Challenge on Bokeh Effect Synthesis: Methods and Results

Andrey Ignatov, Praveen Kandula, Maitreya Suin, A. N. Rajagopalan, Zhiwei Xiong, Jie Huang, Guanting Dong, Mingde Yao, Dong Liu, Wenjin Yang, Ming Hong, Wenying Lin, Jagruti Patel, Yanyun Qu, Jae-Seok Choi, Woonsung Park, Munchurl Kim, Rui Liu, Xiangyu Mao, Chengxi Yang, Qiong Yan, Wenxiu Sun, Junkai Fang, Radu Timofte, Meimei Shang, Fei Gao, Sujoy Ghosh, Prasen Kumar Sharma, Arijit Sur, Bolun Zheng, Xin Ye, Li Huang, Xiang Tian, Saikat Dutta, Kuldeep Purohit
ICCVW 2019 pp. 3591-3598
doi:10.1109/ICCVW.2019.00444 /iccvw/2019/ignatov2019iccvw-aim/

Abstract

This paper reviews the first AIM challenge on bokeh effect synthesis with the focus on proposed solutions and results. The participating teams were solving a real-world image-to-image mapping problem, where the goal was to map standard narrow-aperture photos to the same photos captured with a shallow depth-of-field by the Canon 70D DSLR camera. In this task, the participants had to restore 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 fidelity scores (PSNR and SSIM) with solutions' perceptual results measured in a user study. The proposed solutions significantly improved baseline results, defining the state-of-the-art for practical bokeh effect simulation.

ICCVW Semantic Scholar

Cite

Text

Ignatov et al. "AIM 2019 Challenge on Bokeh Effect Synthesis: Methods and Results." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00444

Markdown

[Ignatov et al. "AIM 2019 Challenge on Bokeh Effect Synthesis: Methods and Results." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/ignatov2019iccvw-aim/) doi:10.1109/ICCVW.2019.00444

BibTeX

@inproceedings{ignatov2019iccvw-aim,
  title     = {{AIM 2019 Challenge on Bokeh Effect Synthesis: Methods and Results}},
  author    = {Ignatov, Andrey and Kandula, Praveen and Suin, Maitreya and Rajagopalan, A. N. and Xiong, Zhiwei and Huang, Jie and Dong, Guanting and Yao, Mingde and Liu, Dong and Yang, Wenjin and Hong, Ming and Lin, Wenying and Patel, Jagruti and Qu, Yanyun and Choi, Jae-Seok and Park, Woonsung and Kim, Munchurl and Liu, Rui and Mao, Xiangyu and Yang, Chengxi and Yan, Qiong and Sun, Wenxiu and Fang, Junkai and Timofte, Radu and Shang, Meimei and Gao, Fei and Ghosh, Sujoy and Sharma, Prasen Kumar and Sur, Arijit and Zheng, Bolun and Ye, Xin and Huang, Li and Tian, Xiang and Dutta, Saikat and Purohit, Kuldeep},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2019},
  pages     = {3591-3598},
  doi       = {10.1109/ICCVW.2019.00444},
  url       = {https://mlanthology.org/iccvw/2019/ignatov2019iccvw-aim/}
}