BokehMe: When Neural Rendering Meets Classical Rendering
This work addresses the need for adjustable bokeh rendering in photography and graphics, though it is incremental as it builds on existing neural and classical methods.
The authors tackled the problem of generating high-resolution photo-realistic bokeh effects from a single image with imperfect disparity maps by proposing BokehMe, a hybrid framework combining neural and classical rendering, which outperformed previous methods in experiments and a user study.
We propose BokehMe, a hybrid bokeh rendering framework that marries a neural renderer with a classical physically motivated renderer. Given a single image and a potentially imperfect disparity map, BokehMe generates high-resolution photo-realistic bokeh effects with adjustable blur size, focal plane, and aperture shape. To this end, we analyze the errors from the classical scattering-based method and derive a formulation to calculate an error map. Based on this formulation, we implement the classical renderer by a scattering-based method and propose a two-stage neural renderer to fix the erroneous areas from the classical renderer. The neural renderer employs a dynamic multi-scale scheme to efficiently handle arbitrary blur sizes, and it is trained to handle imperfect disparity input. Experiments show that our method compares favorably against previous methods on both synthetic image data and real image data with predicted disparity. A user study is further conducted to validate the advantage of our method.