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.
翻译:Bokeh效应是拍摄艺术和美学照片的最理想效果之一。通常,它需要一台具有不同孔径和百叶窗设置的DSLR相机和某些摄影技能来产生这种效果。在智能手机中,计算方法和额外的传感器用来克服物理镜头和感应限制,以达到这种效果。大多数现有方法都使用了额外的传感器数据或预先训练的网络,以对场景进行精细深度估计,有时对图像中的分块突出对象使用肖像分解预培训的网络模块。由于这些原因,网络有许多参数,在运行时密集,无法在中程设备中运行。在本文件中,我们使用了终端到终端深度多层高层次网络(DMSHN)模型,用于直接提供从单层相机拍摄的图像和感知效果。为了进一步提高这种效果的感知质量,还提出了由两个DMSHN模块组成的堆叠式模型。我们的模型并不依靠任何预先训练的网络模块,用于单层深度的DSimation或盐度检测。在本文中,我们使用了一个端端端端端至端的高级图像质量模型,从而大大缩小了目前S-HDMSten-rod-rod-mod-mod-rod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mod-mo