Variable Aperture Bokeh Rendering via Customized Focal Plane Guidance
Kang Chen, Shijun Yan, Aiwen Jiang, Han Li, Zhifeng Wang

TL;DR
This paper introduces a controllable bokeh rendering method that allows precise focal plane and aperture customization, supported by a new dataset, achieving realistic effects with a lightweight model.
Contribution
It presents a novel controllable bokeh rendering approach with user-defined focal and aperture control, and introduces the Variable Aperture Bokeh Dataset (VABD) for improved learning.
Findings
Achieved state-of-the-art bokeh rendering performance.
Model is lightweight with only 4.4 million parameters.
Demonstrated effectiveness on public and new datasets.
Abstract
Bokeh rendering is one of the most popular techniques in photography. It can make photographs visually appealing, forcing users to focus their attentions on particular area of image. However, achieving satisfactory bokeh effect usually presents significant challenge, since mobile cameras with restricted optical systems are constrained, while expensive high-end DSLR lens with large aperture should be needed. Therefore, many deep learning-based computational photography methods have been developed to mimic the bokeh effect in recent years. Nevertheless, most of these methods were limited to rendering bokeh effect in certain single aperture. There lacks user-friendly bokeh rendering method that can provide precise focal plane control and customised bokeh generation. There as well lacks authentic realistic bokeh dataset that can potentially promote bokeh learning on variable apertures. To…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRobotics and Sensor-Based Localization · Inertial Sensor and Navigation · Advanced Image and Video Retrieval Techniques
MethodsFocus
