This study presents the outcomes of the first Controllable Bokeh Rendering Challenge at NTIRE and highlights the most effective submitted methodologies. In total, 44 participants registered for the competition, of which 8 teams submitted valid solutions after the conclusion of the final test phase. All submissions were evaluated on unseen images, focusing on portraits and intricate subjects with complex and visually appealing bokeh phenomena. In addition to the first track focusing on established quantitative fidelity metrics, we conducted a qualitative user study with a panel of experts for a second track focusing on perceptual assessment. As this was the inaugural challenge on this topic, most of the participants focused on refining and extending the Bokehlicious baseline method.
@article{arxiv.2605.05510,
title = {The First Controllable Bokeh Rendering Challenge at NTIRE 2026},
author = {Tim Seizinger and Florin-Alexandru Vasluianu and Jeffrey Chen and Zhuyun Zhou and Zongwei Wu and Radu Timofte and Dafeng Zhang and Yipeng Lin and Qi Yan and Junhao Chen and Yang Yang and Divyavardhan Singh and Hariom Thacker and Hammad Mohammad and Aanchal Maurya and Kishor Upla and Kiran Raja and Wei Zhou and Hongyu Huang and Yujin Cho and Grigory Malivenko and Jiachen Tu and Yaokun Shi and Guoyi Xu and Yaoxin Jiang and Jiajia Liu},
journal= {arXiv preprint arXiv:2605.05510},
year = {2026}
}
Comments
Challenge report paper from NTIRE Workshop at CVPR 2026