AIM 2020 Challenge on Rendering Realistic Bokeh

TL;DR

This paper reviews the AIM 2020 challenge on realistic bokeh rendering, highlighting solutions that improve state-of-the-art methods for single-image shallow depth-of-field simulation using a large dataset and practical evaluation metrics.

Contribution

It presents novel solutions that significantly outperform baselines in realistic bokeh rendering, emphasizing efficiency and perceptual quality in real-world scenarios.

Findings

Proposed solutions outperform baseline results.

Models achieve real-time performance on desktop and mobile devices.

State-of-the-art accuracy in single-image bokeh simulation.

Abstract

This paper reviews the second AIM realistic bokeh effect rendering challenge and provides the description of the proposed solutions and results. The participating teams were solving a real-world bokeh simulation problem, where the goal was to learn a realistic shallow focus technique using a large-scale EBB! bokeh dataset consisting of 5K shallow / wide depth-of-field image pairs captured using the Canon 7D DSLR camera. The participants had to render 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 the runtime and the perceptual quality of the solutions measured in the user study. To ensure the efficiency of the submitted models, we measured their runtime on standard desktop CPUs as well as were running the models on smartphone GPUs. The proposed solutions significantly improved the baseline results, defining the state-of-the-art for practical bokeh effect rendering problem.