Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report
This addresses the limitation of mobile cameras in producing bokeh effects, offering an AI-based solution for smartphone photography, though it is incremental as part of a challenge report.
The paper tackled the problem of rendering realistic bokeh effects on mobile cameras using deep learning, with models developed in a challenge achieving efficient runtime on smartphone GPUs, specifically evaluated on the Kirin 9000's Mali GPU.
As mobile cameras with compact optics are unable to produce a strong bokeh effect, lots of interest is now devoted to deep learning-based solutions for this task. In this Mobile AI challenge, the target was to develop an efficient end-to-end AI-based bokeh effect rendering approach that can run on modern smartphone GPUs using TensorFlow Lite. The participants were provided with a large-scale EBB! bokeh dataset consisting of 5K shallow / wide depth-of-field image pairs captured using the Canon 7D DSLR camera. The runtime of the resulting models was evaluated on the Kirin 9000's Mali GPU that provides excellent acceleration results for the majority of common deep learning ops. A detailed description of all models developed in this challenge is provided in this paper.