This letter presents an automatic 2D-to-3D conversion method using a structure from motion (SfM) process for multi-object scenes. The foreground and background regions may have different depth values in an image. First, we detect the foreground objects and the background by using a depth histogram. Then, the proposed method creates the virtual image by projecting each region with its computed projective matrix. Experimental results compared to previous research show that the proposed method provides realistic stereoscopic images.
Hak Gu KIM
Inha University
Jin-ku KANG
Inha University
Byung Cheol SONG
Inha University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hak Gu KIM, Jin-ku KANG, Byung Cheol SONG, "Automatic SfM-Based 2D-to-3D Conversion for Multi-Object Scenes" in IEICE TRANSACTIONS on Fundamentals,
vol. E97-A, no. 5, pp. 1159-1161, May 2014, doi: 10.1587/transfun.E97.A.1159.
Abstract: This letter presents an automatic 2D-to-3D conversion method using a structure from motion (SfM) process for multi-object scenes. The foreground and background regions may have different depth values in an image. First, we detect the foreground objects and the background by using a depth histogram. Then, the proposed method creates the virtual image by projecting each region with its computed projective matrix. Experimental results compared to previous research show that the proposed method provides realistic stereoscopic images.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E97.A.1159/_p
Copy
@ARTICLE{e97-a_5_1159,
author={Hak Gu KIM, Jin-ku KANG, Byung Cheol SONG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Automatic SfM-Based 2D-to-3D Conversion for Multi-Object Scenes},
year={2014},
volume={E97-A},
number={5},
pages={1159-1161},
abstract={This letter presents an automatic 2D-to-3D conversion method using a structure from motion (SfM) process for multi-object scenes. The foreground and background regions may have different depth values in an image. First, we detect the foreground objects and the background by using a depth histogram. Then, the proposed method creates the virtual image by projecting each region with its computed projective matrix. Experimental results compared to previous research show that the proposed method provides realistic stereoscopic images.},
keywords={},
doi={10.1587/transfun.E97.A.1159},
ISSN={1745-1337},
month={May},}
Copy
TY - JOUR
TI - Automatic SfM-Based 2D-to-3D Conversion for Multi-Object Scenes
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1159
EP - 1161
AU - Hak Gu KIM
AU - Jin-ku KANG
AU - Byung Cheol SONG
PY - 2014
DO - 10.1587/transfun.E97.A.1159
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E97-A
IS - 5
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - May 2014
AB - This letter presents an automatic 2D-to-3D conversion method using a structure from motion (SfM) process for multi-object scenes. The foreground and background regions may have different depth values in an image. First, we detect the foreground objects and the background by using a depth histogram. Then, the proposed method creates the virtual image by projecting each region with its computed projective matrix. Experimental results compared to previous research show that the proposed method provides realistic stereoscopic images.
ER -