Wide-baseline multi-view video segmentation for 3D reconstruction
Wide-baseline multi-view video segmentation for 3D reconstruction
Obtaining a foreground silhouette across multiple views is one of the fundamental steps in 3D reconstruction. In this paper we present a novel video segmentation approach, to obtain a foreground silhouette, for scenes captured by a wide-baseline camera rig given a sparse manual interaction in a single view. The algorithm is based on trimap propagation, a framework used in video matting. Bayesian inference coupled with camera calibration information are used to spatio-temporally propagate high confidence trimap labels across the multi-view video to obtain coarse silhouettes which are later refined using a matting algorithm. Recent techniques have been developed for foreground segmentation, based on image matting, in multiple views but they are limited to narrow baseline with low foreground variation. The proposed wide-baseline silhouette propagation is robust to inter-view foreground appearance changes, shadows and similarity in foreground/background appearance. The approach has demonstrated good performance in silhouette estimation for views up to 180° baseline (opposing views). The segmentation technique has been fully integrated in a multi-view reconstruction pipeline. The results obtained demonstrate the suitability of the technique for multi-view reconstruction with wide-baseline camera set-ups and natural background.
3D reconstruction, Bayesian inference, Camera calibration, Foreground segmentation, Foreground/background, Fully integrated, High confidence, Image matting, Manual interaction, Multi-view reconstruction, Multi-views, Multiple views, Multiview video, Natural backgrounds, Segmentation, Segmentation techniques, Set-ups, Silhouette, Video matting, Video segmentation, Wide baselines, Algorithms, Bayesian networks, Cameras, Image segmentation, Inference engines, Video signal processing, Three dimensional
13-18
Sarim, M.
1242380f-3b23-491b-ab75-85daccc93f92
Hilton, Adrian
12782a55-4c4d-4dfb-a690-62505f6665db
Guillemaut, J.-Y.
fcaefbd8-8ba1-4c43-978c-0b5d432a3285
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Takai, T.
53894c03-6042-4bc8-86fb-692161fd22bb
2010
Sarim, M.
1242380f-3b23-491b-ab75-85daccc93f92
Hilton, Adrian
12782a55-4c4d-4dfb-a690-62505f6665db
Guillemaut, J.-Y.
fcaefbd8-8ba1-4c43-978c-0b5d432a3285
Kim, H.
2c7c135c-f00b-4409-acb2-85b3a9e8225f
Takai, T.
53894c03-6042-4bc8-86fb-692161fd22bb
Sarim, M., Hilton, Adrian, Guillemaut, J.-Y., Kim, H. and Takai, T.
(2010)
Wide-baseline multi-view video segmentation for 3D reconstruction.
ACM Workshop on 3D Video Processing, , Firenze, Italy.
30 Sep 2010.
.
(doi:10.1145/1877791.1877795).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Obtaining a foreground silhouette across multiple views is one of the fundamental steps in 3D reconstruction. In this paper we present a novel video segmentation approach, to obtain a foreground silhouette, for scenes captured by a wide-baseline camera rig given a sparse manual interaction in a single view. The algorithm is based on trimap propagation, a framework used in video matting. Bayesian inference coupled with camera calibration information are used to spatio-temporally propagate high confidence trimap labels across the multi-view video to obtain coarse silhouettes which are later refined using a matting algorithm. Recent techniques have been developed for foreground segmentation, based on image matting, in multiple views but they are limited to narrow baseline with low foreground variation. The proposed wide-baseline silhouette propagation is robust to inter-view foreground appearance changes, shadows and similarity in foreground/background appearance. The approach has demonstrated good performance in silhouette estimation for views up to 180° baseline (opposing views). The segmentation technique has been fully integrated in a multi-view reconstruction pipeline. The results obtained demonstrate the suitability of the technique for multi-view reconstruction with wide-baseline camera set-ups and natural background.
This record has no associated files available for download.
More information
Published date: 2010
Venue - Dates:
ACM Workshop on 3D Video Processing, , Firenze, Italy, 2010-09-30 - 2010-09-30
Keywords:
3D reconstruction, Bayesian inference, Camera calibration, Foreground segmentation, Foreground/background, Fully integrated, High confidence, Image matting, Manual interaction, Multi-view reconstruction, Multi-views, Multiple views, Multiview video, Natural backgrounds, Segmentation, Segmentation techniques, Set-ups, Silhouette, Video matting, Video segmentation, Wide baselines, Algorithms, Bayesian networks, Cameras, Image segmentation, Inference engines, Video signal processing, Three dimensional
Identifiers
Local EPrints ID: 440578
URI: http://eprints.soton.ac.uk/id/eprint/440578
PURE UUID: 7643379d-f16c-4120-9ff4-b1006fd178e5
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:
H. Kim
Author:
T. Takai
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