“Virtual view generation by linear processing of two differently focused images” by Kubota and Aizawa

  • ©Akira Kubota and Kiyoharu Aizawa



Interest Area:



    Virtual view generation by linear processing of two differently focused images

Session/Category Title:   Color & Focus



    In this sketch, we present a novel approach to image-based rendering (IBR) techniques for generating a virtual view image from different positions with arbitrary focus using two differently focused images captured from a fixed position. In the conventional approach [Potmesil and Chakravarty 1981], focus blur have been produced by applying a realistic camera model to given 3D objects. We propose here a much simpler and more effective method only using space-invariant filters to render both parallax and focusing effects on objects in a scene, according to the virtual camera’s position and focus depth respectively. The proposed method does not need any segmentation and 3D modeling.


    1. Aizawa, K., Kodama, K., and Kubota, A. 2000. Producing object-based special effects by fusing multiple differently focused images. IEEE transactions on Circuits and Systems for Video Technology, 3D special issue 10, 2, 323–330.
    2. Potmesil, M., and Chakravarty, I. 1981. A lens and aperture camera model for synthetic image generation. Computer Graphics 15, 3, 297–305.

ACM Digital Library Publication:

Overview Page: