BokehOrNot: Transforming Bokeh Effect with Image Transformer and Lens Metadata Embedding
This work addresses a domain-specific problem in computational photography for enhancing image aesthetics, but it is incremental as it builds on existing bokeh rendering and image restoration techniques.
The paper tackles the problem of bokeh effect transformation, which involves generating specific bokeh effects across different lens and aperture combinations, and proposes the BokehOrNot model that outperforms current leading models in rendering visually natural effects.
Bokeh effect is an optical phenomenon that offers a pleasant visual experience, typically generated by high-end cameras with wide aperture lenses. The task of bokeh effect transformation aims to produce a desired effect in one set of lenses and apertures based on another combination. Current models are limited in their ability to render a specific set of bokeh effects, primarily transformations from sharp to blur. In this paper, we propose a novel universal method for embedding lens metadata into the model and introducing a loss calculation method using alpha masks from the newly released Bokeh Effect Transformation Dataset(BETD) [3]. Based on the above techniques, we propose the BokehOrNot model, which is capable of producing both blur-to-sharp and sharp-to-blur bokeh effect with various combinations of lenses and aperture sizes. Our proposed model outperforms current leading bokeh rendering and image restoration models and renders visually natural bokeh effects. Our code is available at: https://github.com/indicator0/bokehornot.