Direct virtual viewpoint synthesis from multiple viewpoints

Yi Ding; DW Redmill

doi:10.1109/ICIP.2005.1529933

Abstract

This paper presents a novel approach for synthesizing intermediate or virtual viewpoints (VVs) of a 3D scene based on information from a number of known reference viewpoints (RVs). The proposed approach directly estimates the pixel value (and corresponding depth) for each pixel in the VV. This is contrast to the more traditional 2 stage approach of firstly building a full 3D or 2.5D model for the scene and then synthesising the desired VV. The potential advantage of this approach is that it works directly with the target virtual view and is hopefully less susceptible to the propagation of errors from the depth estimation stage to the interpolation stage

Original language	English
Pages	1045 - 1048
DOIs	https://doi.org/10.1109/ICIP.2005.1529933
Publication status	Published - Sept 2005

Bibliographical note

Terms of use: Copyright © 2005 IEEE. Reprinted from IEEE International Conference on Image Processing, 2005 (ICIP 2005).

This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected].

By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

Name of Conference: International Conference on Image Processing

Keywords

depth estimation
direct viewpoint synthesis

Access to Document

10.1109/ICIP.2005.1529933

Ding IEEE ICIP 2005Accepted author manuscript, 580 KB

http://hdl.handle.net/1983/1521

Handle.net

Persistent link

Cite this

@conference{2989d57ae9a741249ae59034cf60e62d,

title = "Direct virtual viewpoint synthesis from multiple viewpoints",

abstract = "This paper presents a novel approach for synthesizing intermediate or virtual viewpoints (VVs) of a 3D scene based on information from a number of known reference viewpoints (RVs). The proposed approach directly estimates the pixel value (and corresponding depth) for each pixel in the VV. This is contrast to the more traditional 2 stage approach of firstly building a full 3D or 2.5D model for the scene and then synthesising the desired VV. The potential advantage of this approach is that it works directly with the target virtual view and is hopefully less susceptible to the propagation of errors from the depth estimation stage to the interpolation stage",

keywords = "depth estimation, direct viewpoint synthesis",

author = "Yi Ding and DW Redmill",

note = "Terms of use: Copyright {\textcopyright} 2005 IEEE. Reprinted from IEEE International Conference on Image Processing, 2005 (ICIP 2005). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it. Name of Conference: International Conference on Image Processing",

year = "2005",

month = sep,

doi = "10.1109/ICIP.2005.1529933",

language = "English",

pages = "1045 -- 1048",

}

TY - CONF

T1 - Direct virtual viewpoint synthesis from multiple viewpoints

AU - Ding, Yi

AU - Redmill, DW

N1 - Terms of use: Copyright © 2005 IEEE. Reprinted from IEEE International Conference on Image Processing, 2005 (ICIP 2005). This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of Bristol's products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to [email protected]. By choosing to view this document, you agree to all provisions of the copyright laws protecting it. Name of Conference: International Conference on Image Processing

PY - 2005/9

Y1 - 2005/9

N2 - This paper presents a novel approach for synthesizing intermediate or virtual viewpoints (VVs) of a 3D scene based on information from a number of known reference viewpoints (RVs). The proposed approach directly estimates the pixel value (and corresponding depth) for each pixel in the VV. This is contrast to the more traditional 2 stage approach of firstly building a full 3D or 2.5D model for the scene and then synthesising the desired VV. The potential advantage of this approach is that it works directly with the target virtual view and is hopefully less susceptible to the propagation of errors from the depth estimation stage to the interpolation stage

AB - This paper presents a novel approach for synthesizing intermediate or virtual viewpoints (VVs) of a 3D scene based on information from a number of known reference viewpoints (RVs). The proposed approach directly estimates the pixel value (and corresponding depth) for each pixel in the VV. This is contrast to the more traditional 2 stage approach of firstly building a full 3D or 2.5D model for the scene and then synthesising the desired VV. The potential advantage of this approach is that it works directly with the target virtual view and is hopefully less susceptible to the propagation of errors from the depth estimation stage to the interpolation stage

KW - depth estimation

KW - direct viewpoint synthesis

U2 - 10.1109/ICIP.2005.1529933

DO - 10.1109/ICIP.2005.1529933

M3 - Conference Abstract

SP - 1045

EP - 1048

ER -