Rendering Natural Camera Bokeh Effect with Deep Learning
CVPR Workshops(2020)
摘要
Bokeh is an important artistic effect used to highlight the main object of interest on the photo by blurring all out-of-focus areas. While DSLR and system camera lenses can render this effect naturally, mobile cameras are unable to produce shallow depth-of-field photos due to a very small aperture diameter of their optics. Unlike the current solutions simulating bokeh by applying Gaussian blur to image background, in this paper we propose to learn a realistic shallow focus technique directly from the photos produced by DSLR cameras. For this, we present a large-scale bokeh dataset consisting of 5K shallow / wide depth-of-field image pairs captured using the Canon 7D DSLR with 50mm f/1.8 lenses. We use these images to train a deep learning model to reproduce a natural bokeh effect based on a single narrow-aperture image. The experimental results show that the proposed approach is able to render a plausible non-uniform bokeh even in case of complex input data with multiple objects. The dataset, pre-trained models and codes used in this paper are available on the project website.
更多查看译文
关键词
system camera lenses,mobile cameras,depth-of-field photos,Gaussian blur,large-scale bokeh dataset,depth-of-field image pairs,deep learning model,natural bokeh effect,nonuniform bokeh,natural camera bokeh effect,single narrow-aperture imaging,Canon7D DSLR cameras,shallow focus technique,size 50.0 mm
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要