Partial plane sweep volume for deep learning based view synthesis

Kouta Takeuchi; Kazuki Okami; Daisuke Ochi; Hideaki Kimata

doi:10.1145/3102163.3102220

Partial plane sweep volume for deep learning based view synthesis

Kouta Takeuchi, Kazuki Okami, Daisuke Ochi, Hideaki Kimata

Tohoku Medical Megabank Organization (ToMMo)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

We propose a partial plane sweep volume that can be a more suitable input format for deep-learning-based view synthesis approaches. Our approach makes it possible to synthesize higher quality images with a smaller number of learning iterations, while keeping the number of depth planes.

Original language	English
Title of host publication	ACM SIGGRAPH 2017 Posters, SIGGRAPH 2017
Publisher	Association for Computing Machinery, Inc
ISBN (Electronic)	9781450350150
DOIs	https://doi.org/10.1145/3102163.3102220
Publication status	Published - 2017 Jul 30
Event	44th International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2017 - Los Angeles, United States Duration: 2017 Jul 30 → 2017 Aug 3

Publication series

Name	ACM SIGGRAPH 2017 Posters, SIGGRAPH 2017

Other

Other	44th International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2017
Country/Territory	United States
City	Los Angeles
Period	17/7/30 → 17/8/3

Keywords

Novel view synthesis
Plane sweep volume

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Software
Computer Graphics and Computer-Aided Design

Access to Document

10.1145/3102163.3102220

Cite this

Takeuchi, K, Okami, K, Ochi, D & Kimata, H 2017, Partial plane sweep volume for deep learning based view synthesis. in ACM SIGGRAPH 2017 Posters, SIGGRAPH 2017., a83, ACM SIGGRAPH 2017 Posters, SIGGRAPH 2017, Association for Computing Machinery, Inc, 44th International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2017 , Los Angeles, United States, 17/7/30. https://doi.org/10.1145/3102163.3102220

@inproceedings{e54315a16d674c029754006d1d21f602,

title = "Partial plane sweep volume for deep learning based view synthesis",

abstract = "We propose a partial plane sweep volume that can be a more suitable input format for deep-learning-based view synthesis approaches. Our approach makes it possible to synthesize higher quality images with a smaller number of learning iterations, while keeping the number of depth planes.",

keywords = "Novel view synthesis, Plane sweep volume",

author = "Kouta Takeuchi and Kazuki Okami and Daisuke Ochi and Hideaki Kimata",

note = "Publisher Copyright: {\textcopyright} 2017 Copyright held by the owner/author(s).; 44th International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2017 ; Conference date: 30-07-2017 Through 03-08-2017",

year = "2017",

month = jul,

day = "30",

doi = "10.1145/3102163.3102220",

language = "English",

series = "ACM SIGGRAPH 2017 Posters, SIGGRAPH 2017",

publisher = "Association for Computing Machinery, Inc",

booktitle = "ACM SIGGRAPH 2017 Posters, SIGGRAPH 2017",

}

TY - GEN

T1 - Partial plane sweep volume for deep learning based view synthesis

AU - Takeuchi, Kouta

AU - Okami, Kazuki

AU - Ochi, Daisuke

AU - Kimata, Hideaki

PY - 2017/7/30

Y1 - 2017/7/30

N2 - We propose a partial plane sweep volume that can be a more suitable input format for deep-learning-based view synthesis approaches. Our approach makes it possible to synthesize higher quality images with a smaller number of learning iterations, while keeping the number of depth planes.

AB - We propose a partial plane sweep volume that can be a more suitable input format for deep-learning-based view synthesis approaches. Our approach makes it possible to synthesize higher quality images with a smaller number of learning iterations, while keeping the number of depth planes.

KW - Novel view synthesis

KW - Plane sweep volume

UR - http://www.scopus.com/inward/record.url?scp=85028609042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028609042&partnerID=8YFLogxK

U2 - 10.1145/3102163.3102220

DO - 10.1145/3102163.3102220

M3 - Conference contribution

AN - SCOPUS:85028609042

T3 - ACM SIGGRAPH 2017 Posters, SIGGRAPH 2017

BT - ACM SIGGRAPH 2017 Posters, SIGGRAPH 2017

PB - Association for Computing Machinery, Inc

T2 - 44th International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH 2017

Y2 - 30 July 2017 through 3 August 2017

ER -

Partial plane sweep volume for deep learning based view synthesis

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this