Natural image matting for multiple wide-baseline views
Natural image matting for multiple wide-baseline views
In this paper we present a novel approach to estimate the alpha mattes of a foreground object captured by a widebaseline circular camera rig provided a single key frame trimap. Bayesian inference coupled with camera calibration information are used to propagate high confidence trimaps labels across the views. Recent techniques have been developed to estimate an alpha matte of an image using multiple views but they are limited to narrow baseline views with low foreground variation. The proposed wide-baseline trimap propagation is robust to inter-view foreground appearance changes, shadows and similarity in foreground/background appearance for cameras with opposing views enabling high quality alpha matte extraction using any state-of-the-art image matting algorithm. © 2010 IEEE.
Alpha matte, Image matting, Multiple views, Trimap, Wide baselines, Bayesian networks, Image processing, Imaging systems, Inference engines, Cameras
2233-2236
Sarim, M.
1242380f-3b23-491b-ab75-85daccc93f92
Hilton, Adrian
12782a55-4c4d-4dfb-a690-62505f6665db
Guillemaut, J.-Y.
fcaefbd8-8ba1-4c43-978c-0b5d432a3285
Takai, T.
53894c03-6042-4bc8-86fb-692161fd22bb
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
3 December 2010
Sarim, M.
1242380f-3b23-491b-ab75-85daccc93f92
Hilton, Adrian
12782a55-4c4d-4dfb-a690-62505f6665db
Guillemaut, J.-Y.
fcaefbd8-8ba1-4c43-978c-0b5d432a3285
Takai, T.
53894c03-6042-4bc8-86fb-692161fd22bb
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Sarim, M., Hilton, Adrian, Guillemaut, J.-Y., Takai, T. and Kim, H.
(2010)
Natural image matting for multiple wide-baseline views.
17th IEEE International Conference on Image Processing, Hong Kong.
26 - 29 Sep 2010.
.
(doi:10.1109/ICIP.2010.5651610).
Record type:
Conference or Workshop Item
(Paper)
Abstract
In this paper we present a novel approach to estimate the alpha mattes of a foreground object captured by a widebaseline circular camera rig provided a single key frame trimap. Bayesian inference coupled with camera calibration information are used to propagate high confidence trimaps labels across the views. Recent techniques have been developed to estimate an alpha matte of an image using multiple views but they are limited to narrow baseline views with low foreground variation. The proposed wide-baseline trimap propagation is robust to inter-view foreground appearance changes, shadows and similarity in foreground/background appearance for cameras with opposing views enabling high quality alpha matte extraction using any state-of-the-art image matting algorithm. © 2010 IEEE.
This record has no associated files available for download.
More information
Published date: 3 December 2010
Venue - Dates:
17th IEEE International Conference on Image Processing, Hong Kong, 2010-09-26 - 2010-09-29
Keywords:
Alpha matte, Image matting, Multiple views, Trimap, Wide baselines, Bayesian networks, Image processing, Imaging systems, Inference engines, Cameras
Identifiers
Local EPrints ID: 440576
URI: http://eprints.soton.ac.uk/id/eprint/440576
PURE UUID: 43573101-9818-45fb-9e6b-626feb0893fa
Catalogue record
Date deposited: 07 May 2020 16:37
Last modified: 17 Mar 2024 04:01
Export record
Altmetrics
Contributors
Author:
M. Sarim
Author:
Adrian Hilton
Author:
J.-Y. Guillemaut
Author:
T. Takai
Author:
H. Kim
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics