Main > Acta Optica Sinica >  Volume 40 >  Issue 1 >  Page 0111021 > Article
  • Abstract
  • Abstract
  • View Summary
  • Figures (9)
  • Tables (2)
  • Equations (0)
  • References (19)
  • Get PDF(in Chinese)
  • Paper Information
  • Received: Aug. 5, 2019

    Accepted: Nov. 6, 2019

    Posted: Jan. 1, 2020

    Published Online: Jan. 6, 2020

    The Author Email: Fu Yutian (yutianfu@mail.sitp.ac.cn)

    DOI: 10.3788/AOS202040.0111021

  • Get Citation
  • Copy Citation Text

    Qi Wang, Yutian Fu. Single-Image Refocusing Using Light Field Synthesis and Circle of Confusion Rendering[J]. Acta Optica Sinica, 2020, 40(1): 0111021

    Download Citation

  • Category
  • Special Issue on Computational Optical Imaging
  • Share
Acta Optica Sinica, Vol. 40, Issue 1, 0111021 (2020)

Single-Image Refocusing Using Light Field Synthesis and Circle of Confusion Rendering

Wang Qi1,2,3 and Fu Yutian1,2,*

Author Affiliations

  • 1Key Laboratory of Infrared System Detection and Imaging, Chinese Academy of Sciences, Shanghai 200083, China
  • 2Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China
  • 3University of Chinese Academy of Sciences, Beijing 100049, China

Abstract

A method to dynamically refocus a single image is presented; by combining deep learning-based light field synthesis with geometric structure-based circle of confusion rendering, it simulates the light field refocusing effect. In the proposed method, the depth map is estimated and converted into disparity, and then the circle of confusion diameter is measured at different depths to resample the pixels. Two neural network structures are designed, supervised by multi-views and refocused images of the light field camera. Experiments are conducted on multiple datasets and real scenes. Compared with other techniques, the results obtained using the proposed method show superior visual performance and evaluation indicators, along with an acceptable computational cost, with the peak signal-to-noise ratio and structural similarity index reaching 34.55 and 0.937, respectively.

keywords

Please Enter Your Email: