Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 Challenge: Report
METADATA ONLY
Loading...
Author / Producer
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.
Permanent link
Publication status
published
External links
Book title
Computer Vision – ECCV 2022 Workshops. ECCV 2022
Journal / series
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)