Share Email Print

Proceedings Paper

A modified non-local mean inpainting technique for occlusion filling in depth-image-based rendering
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

'View plus depth' is an attractive compact representation format for 3D video compression and transmission. It combines 2D video with depth map sequence aligned in a per-pixel manner to represent the moving 3D scene in interest. Any different-perspective view can be synthesized out if this representation through Depth-Image Based Rendering (DIBR). However, such rendering is prone to disocclusion errors: regions originally covered by foreground objects become visible in the synthesized view and have to be filled with perceptually-meaningful data. In this work, a technique for reducing the perceived artifacts by inpainting the disoccluded areas is proposed. Based on Criminisi's exemplar-based inpainting algorithm, the developed technique recovers the disoccluded areas by using pixels of similar blocks surrounding it. In the original work, a moving window is centered on the boundaries between known and unknown parts ('target window'). The known pixels are used to select windows which are most similar to the target one. When this process is completed, the unknown region of the target patch is filled with a weighted combination of pixels from the selected windows. In the proposed scheme, the priority map, which defines the rule for selecting the order of pixels to be filled, has been modified to meet the requirement for disocclusion hole filling and a better non-local mean estimate has been suggested accordingly. Furthermore, the search for similar patches has also been extended to previous and following frames of the video under processing, thus improving both computational efficiency and resulting quality.

Paper Details

Date Published: 15 February 2011
PDF: 13 pages
Proc. SPIE 7863, Stereoscopic Displays and Applications XXII, 78631C (15 February 2011); doi: 10.1117/12.872926
Show Author Affiliations
Lucio Azzari, Tampere Univ. of Technology (Finland)
Federica Battisti, Univ. degli Studi di Roma Tre (Italy)
Atanas Gotchev, Tampere Univ. of Technology (Finland)
Marco Carli, Univ. degli Studi di Roma Tre (Italy)
Karen Egiazarian, Tampere Univ. of Technology (Finland)

Published in SPIE Proceedings Vol. 7863:
Stereoscopic Displays and Applications XXII
Andrew J. Woods; Nicolas S. Holliman; Neil A. Dodgson, Editor(s)

© SPIE. Terms of Use
Back to Top