Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 Challenge: Report


METADATA ONLY
Loading...

Date

2023

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

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.

Publication status

published

Book title

Computer Vision – ECCV 2022 Workshops. ECCV 2022

Volume

13803

Pages / Article No.

153 - 173

Publisher

Springer

Event

European Conference on Computer Vision Workshops (ECCV 2022)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Mobile AI challenge; Bokeh; Portrait photos; Mobile cameras; Shallow depth-of-field; Mobile AI; Deep learning; AI Benchmark

Organisational unit

03514 - Van Gool, Luc (emeritus) / Van Gool, Luc (emeritus) check_circle

Notes

Funding

Related publications and datasets