AIM 2019 Challenge on Bokeh Effect Synthesis: Methods and Results

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.

1. Introduction

The topic of image manipulation related to portable smartphone cameras has recently witnessed an increased interest from the vision and graphics communities, with a large number of works being published on different image quality enhancement aspects [7]–[9], [24], [1], photo segmentation and blurring [26], [22], [3], [2], style transfer [4], [12], [16], etc. One of the topics that gained a huge popularity over the past years is an automatic bokeh effect synthesis that can be now found in the majority of smartphone camera applications. The first works on portrait segmentation [10] appeared in 2014, followed by many subsequent papers that have substantially improved the baseline results [22], [28]. A further development in this field was facilitated by work [26] that in detail described a synthetic depth-of-field rendering method used by Google Pixel phones.