BokehMe++: Harmonious Fusion of Classical and Neural Rendering for Versatile Bokeh Creation

Despite significant advancements in simulating the bokeh effect of Digital Single Lens Reflex Camera (DSLR) from an all-in-focus image, challenges remain in processing highlight points, preserving boundary details for in-focus objects and processing high-resolution images efficiently. To tackle these issues, we first develop a ray-tracing-based bokeh simulator. An innovative pipeline with weight redistribution is introduced to handle highlight rendering. By considering the front length of lens barrel, we can simulate realistic cat-eye effect. This bokeh simulator serves as the foundation for creating our training dataset. Building on this dataset, we introduce a hybrid framework BokehMe++, combining a classical renderer and a neural renderer. The classical renderer is implemented by a hierarchical scattering-based method, which suffers from boundary inaccuracies. These erroneous areas will be identified by an error map generator and be corrected by a two-stage neural renderer. Adaptive resizing and iterative upsampling are introduced in the neural renderer to process arbitrary blur size efficiently. Extensive experiments demonstrate that BokehMe++ outperforms existing methods and provides highly customizable rendering features, such as adjustable blur amount, focal plane, highlight mode and cat-eye effect. Furthermore, BokehMe++ can maintain the sharpness of hair details in portraits through an auxiliary alpha map input.

I. Introduction

Bokeh refers to the effect of a soft out-of-focus blur achieved by capturing a subject with a large-aperture lens. This aesthetic effect varies with different lens designs and settings. As smartphones become more integral to our daily lives, the desire to simulate high-quality photographic bokeh effects by smartphones with small-aperture lens grows. As a result, bokeh rendering from an all-in-focus image has emerged as a hot topic within the fields of computer vision and computational photography.