Presentation 2013-09-13
Depth Estimation Method of Multi-viewpoint cameras for multi parallax glasses-free 3D-TV
Hiroshi SANKOH, Sei Naito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a depth estimation algorithm for multi-viewpoint videos whose resolutions are high-definition (1920×1080) and frame rates are 60frames per second. Specifically, the algorithm does not estimate the depth by applying stereo matching between viewpoints, but reconstructs 3-dimensional (3D) model by roughly extracting object candidate regions in a 3D space and deciding the specific object regions based on the color similarity of the surface in the 3D model among multiple cameras. Experimental results revealed that the proposed method successfully estimated the precise depth for multi-view videos compared with the conventional stereo matching method. Furthermore, it was also confirmed that the virtual view videos between real cameras was rendered precisely by applying VSRS to the depth information estimated by the proposed approach.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) glasses-free / 3D / multi-parallax / multi-viewpoint / depth estimation
Paper # LOIS2013-24,IE2013-45,EMM2013-67
Date of Issue

Conference Information
Committee LOIS
Conference Date 2013/9/5(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Life Intelligence and Office Information Systems (LOIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Depth Estimation Method of Multi-viewpoint cameras for multi parallax glasses-free 3D-TV
Sub Title (in English)
Keyword(1) glasses-free
Keyword(2) 3D
Keyword(3) multi-parallax
Keyword(4) multi-viewpoint
Keyword(5) depth estimation
1st Author's Name Hiroshi SANKOH
1st Author's Affiliation KDDI R&D Laboratories Inc.()
2nd Author's Name Sei Naito
2nd Author's Affiliation KDDI R&D Laboratories Inc.
Date 2013-09-13
Paper # LOIS2013-24,IE2013-45,EMM2013-67
Volume (vol) vol.113
Number (no) 210
Page pp.pp.-
#Pages 6
Date of Issue