A modified non-local mean inpainting technique for occlusion filling in depth-image-based rendering

Lucio Azzari; Federica Battisti; Atanas Gotchev; Marco Carli; Karen Egiazarian

doi:10.1117/12.872926

15 February 2011 A modified non-local mean inpainting technique for occlusion filling in depth-image-based rendering

Lucio Azzari, Federica Battisti, Atanas Gotchev, Marco Carli, Karen Egiazarian

Proceedings Volume 7863, Stereoscopic Displays and Applications XXII; 78631C (2011) https://doi.org/10.1117/12.872926
Event: IS&T/SPIE Electronic Imaging, 2011, San Francisco Airport, California, United States

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.

Citation Download Citation

Lucio Azzari, Federica Battisti, Atanas Gotchev, Marco Carli, and Karen Egiazarian "A modified non-local mean inpainting technique for occlusion filling in depth-image-based rendering", Proc. SPIE 7863, Stereoscopic Displays and Applications XXII, 78631C (15 February 2011); https://doi.org/10.1117/12.872926

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available