Litcius/Paper detail

Constrained Predictive Filters for Single Image Bokeh Rendering

Bolun Zheng, Quan Chen, Shanxin Yuan, Xiaofei Zhou, Zhang Hua, Jiyong Zhang, Chenggang Yan, Greg Slabaugh

2022IEEE Transactions on Computational Imaging24 citationsDOIOpen Access PDF

Abstract

Bokeh rendering is a technique used to take pictures with out-of-focus areas to highlight regions of interest. Due to limitations in hardware and shooting condition, rendering a bokeh image from a full-focus image has attracted a lot of interest. In this paper, we model bokeh rendering as the combination of salient region retention and bokeh blurring, and propose a neural network to generate a realistic bokeh image from a single full-focus image through end-to-end training. Specifically, we propose a gate fusion block to estimate the salient area, and introduce a constrained predictive filter for salient region retention and bokeh blurring within a unified architecture. Further, we utilize a pixel coordinate-based map to enhance the training. Experimental results illustrate the effectiveness of our model. The comparison with state-of-the-art methods (PyNET [1], DMSHN [2], BGGAN [3], etc.) shows that our model produces better bokeh effects and retains salient objects.

Topics & Concepts

Rendering (computer graphics)Artificial intelligenceSalientComputer scienceComputer visionImage-based modeling and renderingPixelArtificial neural networkAdvanced Image Processing TechniquesAdvanced Vision and ImagingImage Processing Techniques and Applications
Constrained Predictive Filters for Single Image Bokeh Rendering | Litcius