Depth-guided deep filtering network for efficient single image bokeh rendering
Depth-guided deep filtering network for efficient single image bokeh rendering
复制标题
DOI：
10.1007/s00521-023-08852-y
复制
发表时间：
2023-07-26
影响因子：
6
通讯作者：
Yuan，Shanxin
中科院分区：
文献类型：
--
作者：
Chen，Quan;Zheng，Bolun;Yuan，Shanxin
Bokeh effect is usually used to highlight major contents in an image. Limited by the small sensors, cameras on smartphones are less sensitive to the depth information and cannot directly produce bokeh effect as pleasant as digital single lens reflex cameras. To address this problem, a depth-guided deep filtering network, called DDFN, is proposed in this study. Specifically, the focused region detection block is designed to detect the salient areas, and the depth estimated block is introduced to estimate depth maps from full-focus images. Further, combining depth maps and focused features, an adaptive rendering block is proposed to synthesize bokeh effect with adaptive cross 1-D filters. Both quantitative and qualitative evaluations on the public datasets demonstrate that the proposed model performs favorably against state-of-the-art methods in terms of rendering effects and has lower computational cost, e.g., 24.07 dB PSNR on EBB! dataset and 0.45 s inference times for aimage on a Snapdragon 865 mobile processor.
