Feature Pyramid Boosting Network for Rendering Natural Bokeh

Natural bokeh is a typical characteristic of digital single-lens reflex (DSLR) cameras and high-quality lenses, which is commonly used to emphasize a subject from a distracting background. However, it is still a big challenge for mobile platforms to produce similar effects due to the small apertures of their lenses. Unlike many previous methods formulated as a two-stage task composed of depth/defocus estimation and defocus magnification, we propose a feature pyramid boosting network with novel hierarchical attention modules to render bokeh in one step. In addition, existing learning-based methods suffer from the pixel misalignment of the datasets. We present a well-aligned bokeh dataset captured by a DSLR to address this problem. Experiments show that our method can render comparable bokeh with the state-of-the-art method but requires fewer parameters.