The Bokeh Effect is one of the most desirable effects in photography for
rendering artistic and aesthetic photos. Usually, it requires a DSLR camera
with different aperture and shutter settings and certain photography skills to
generate this effect. In smartphones, computational methods and additional
sensors are used to overcome the physical lens and sensor limitations to
achieve such effect. Most of the existing methods utilized additional sensor's
data or pretrained network for fine depth estimation of the scene and sometimes
use portrait segmentation pretrained network module to segment salient objects
in the image. Because of these reasons, networks have many parameters, become
runtime intensive and unable to run in mid-range devices. In this paper, we
used an end-to-end Deep Multi-Scale Hierarchical Network (DMSHN) model for
direct Bokeh effect rendering of images captured from the monocular camera. To
further improve the perceptual quality of such effect, a stacked model
consisting of two DMSHN modules is also proposed. Our model does not rely on
any pretrained network module for Monocular Depth Estimation or Saliency
Detection, thus significantly reducing the size of model and run time. Stacked
DMSHN achieves state-of-the-art results on a large scale EBB! dataset with
around 6x less runtime compared to the current state-of-the-art model in
processing HD quality images.

本文利用端到端 Deep Multi-Scale Hierarchical Network (DMSHN) 模型对单眼相机拍摄的图片进行了 Bokeh 效果的直接渲染。通过提出一个堆叠的 DMSHN 模型来进一步改善效果，避免在中等配置设备上运行时参数过多、运行时间过长等问题。该模型在使用较小的运行时间处理高清晰度图像时能够获得大规模 EBB! 数据集上的最新成果。