Lens-to-Lens Bokeh Effect Transformation. NTIRE 2023 Challenge Report
V. Monga, Radu Timofte, Xingyi Yang, Ke Xian, Marcos V. Conde, Chengxin Liu, Ziwei Luo, Wenyi Lian, Fredrik K. Gustafsson, Amirsaeed Yazdani, Baoliang Chen, Zhiguo Cao, Songhua Liu, Zheng Zhao, Tim Seizinger, Manuel Kolmet, †. TomE.Bishop, Xianrui Luo, Huiqiang Sun, Liao Shen, Chaowei Liu, Zigeng Chen, Yongcheng Jing, Michael Bi, Mi Wang, Zhihao Yang, Siyuan Lai, Haichuan Zhang, T. Hoang, Jens Sj¨olund, Thomas B. Sch¨on, Yuxuan Zhao, Yiqing Xu•Wed May 31 2023
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge. Recent advancements of mobile photography aim to reach the visual quality of full-frame cameras. Now, a goal in computational photography is to optimize the Bokeh effect itself, which is the aesthetic quality of the blur in out-of-focus areas of an image. Photographers create this aesthetic effect by benefiting from the lens optical properties.The aim of this work is to design a neural network capable of converting the the Bokeh effect of one lens to the effect of another lens without harming the sharp foreground regions in the image. For a given input image, knowing the target lens type, we render or transform the Bokeh effect accordingly to the lens properties. We build the BETD using two full-frame Sony cameras, and diverse lens setups.To the best of our knowledge, we are the first attempt to solve this novel task, and we provide the first BETD dataset and benchmark for it. The challenge had 99 registered participants. The submitted methods gauge the state-of-the-art in Bokeh effect rendering and transformation.
