단일 영상에서 디포커스 맵을 활용한 보케 효과 알고리즘

Bokeh Effect Algorithm using Defocus Map in Single Image

  • 이용환 (원광대학교 디지털콘텐츠공학과) ;
  • 김흥준 (경상국립대학교 자연과학대학 컴퓨터소프트웨어전공)
  • Lee, Yong-Hwan (Dept. of Digital Contents, Wonkwang University) ;
  • Kim, Heung Jun (College of Natural Sciences, Department of Computer Software, Kyeongsang National University)
  • 투고 : 2022.09.08
  • 심사 : 2022.09.17
  • 발행 : 2022.09.30

초록

Bokeh effect is a stylistic technique that can produce blurring the background of photos. This paper implements to produce a bokeh effect with a single image by post processing. Generating depth map is a key process of bokeh effect, and depth map is an image that contains information relating to the distance of the surfaces of scene objects from a viewpoint. First, this work presents algorithms to determine the depth map from a single input image. Then, we obtain a sparse defocus map with gradient ratio from input image and blurred image. Defocus map is obtained by propagating threshold values from edges using matting Laplacian. Finally, we obtain the blurred image on foreground and background segmentation with bokeh effect achieved. With the experimental results, an efficient image processing method with bokeh effect applied using a single image is presented.

키워드

과제정보

본 연구는 2022년도 정부(미래창조과학부)의 재원으로 한국연구재단의 지원을 받아 수행된 기초연구사업임(과제번호: 2021R1A2C1012947).

참고문헌

  1. Nitin Singh, Manoj Kumar, P.J. Mahesh, Rituparna Sarkar, "Depth Aware Portrait Segmentation Using Dual Focus Images", International Conference on Multimedia and Expo (ICME), 2018.
  2. Kushal Singla, Joy Bose, Amith Dsousa, "Bokeh Effect in Images on Objects Based on User Interest", International Conference on Electronics, Computing and Communication Technologies (CONECCT), 2019.
  3. Website, https://developer.apple.com/documentation/avfoundation/additional_data_capture/capturing_photos_with_depth
  4. Abhijith Punnappurath, Abdullah Abuolaim, Mahmoud Afifi, Michael S. Brown, "Modeling Defocus-Disparity in Dual-Pixel Sensors", International Conference on Computational Photography (ICCP), 2020.
  5. Shaojun Liu, Fei Zhou, Qingmin Liao, "Defocus map estimation from a single image based on two-parameter defocus model", IEEE Transactions on Image Processing, vol.25, no.12, pp.5943-5956, 2016. https://doi.org/10.1109/TIP.2016.2617460
  6. J. Elder, S. Zucker, "Local scale control for edge detection and blur estimation", IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol.20, no.7, pp.699-716, 1998. https://doi.org/10.1109/34.689301
  7. S. Bae, F. Durand, "Defocus magnification", Proceedings on Eurographics, pp.571-579, 2007.
  8. A. Levin, R. Fergus, F. Durand, W.T. Freeman, "Image and depth from a conventional camera with a coded aperture", ACM Transactions on Graphics, 2007.
  9. Y.W. Tai, M.S. Brown, "Single image defocus map estimation using local contrast prior", Proceedings on ICIP, 2009.
  10. Anat Levin, Dani Lischinski, Yair Weiss, "A closed-form solution to natural image matting", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.30, no.2, pp.228-242, 2008. https://doi.org/10.1109/TPAMI.2007.1177
  11. Kaiming He, C. Rhemann, C. Rother, Xiaoou Tang, Jian Sun, "A global sampling method for alpha matting", IEEE Conference on Computer Vision and Pattern Recognition, pp.2049-2056, 2011.
  12. Suhasini S Goilkar, Dinkar M Yadav, "Depth Map Estimation of Single Defocused Image", International Conference on Forensics, Analytics, Big Data, Security, 2021.
  13. Ali Karaali, Naomi Harte, Claudio R. Jung, "Deep Multi-Scale Feature Learning for Defocus Blur Estimation", IEEE Transactions on Image Processing, Vol.31, pp.1097-1106, 2022. https://doi.org/10.1109/TIP.2021.3139243
  14. Yawen Lu, Garrett Milliron, John Slagter, Guoyu Lu, "Self-Supervised Single-Image Depth Estimation from Focus and Defocus Clues", IEEE Robotics and Automation Letters, Vol.6, Issue.4, 2021.
  15. Yong-Hwan Lee, Youngseop Kim, "Depth Map Generation Algorithm from Single Defocused Image", Journal of the Semiconductor & Display Technology, Vol.15, No.3, 2016.