Rendering Natural Camera Bokeh Effect With Deep Learning

Andrey Ignatov, Jagruti Patel, Radu Timofte; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2020, pp. 418-419


Bokeh is an important artistic effect used to highlight the main object of interest on the photo by blurring all out-of-focus areas. While DSLR and system camera lenses can render this effect naturally, mobile cameras are unable to produce shallow depth-of-field photos due to a very small aperture diameter of their optics. Unlike the current solutions simulating bokeh by applying Gaussian blur to image background, in this paper we propose to learn a realistic shallow focus technique directly from the photos produced by DSLR cameras. For this, we present a large-scale bokeh dataset consisting of 5K shallow / wide depth-of-field image pairs captured using the Canon 7D DSLR with 50mm f/1.8 lenses. We use these images to train a deep learning model to reproduce a natural bokeh effect based on a single narrow-aperture image. The experimental results show that the proposed approach is able to render a plausible non-uniform bokeh even in case of complex input data with multiple objects. The dataset, pre-trained models and codes used in this paper are available on the project website: ihnatova/pynet-bokeh.html

Related Material

author = {Ignatov, Andrey and Patel, Jagruti and Timofte, Radu},
title = {Rendering Natural Camera Bokeh Effect With Deep Learning},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2020}