Home / Issues / 15.2018 / Interactive Hyper Spectral Image Rendering on GPU
Document Actions

Citation and metadata

Back to the article.

Recommended citation

Romain Hoarau, Eric Coiro, Sébastien Thon, and Romain Raffin, Interactive Hyper Spectral Image Rendering on GPU. Journal of Virtual Reality and Broadcasting, 15(2018), no. 4. (urn:nbn:de:0009-6-48850)

Download Citation

Endnote

%0 Journal Article
%T Interactive Hyper Spectral Image Rendering on GPU
%A Hoarau, Romain
%A Coiro, Eric
%A Thon, Sébastien
%A Raffin, Romain
%J Journal of Virtual Reality and Broadcasting
%D 2019
%V 15(2018)
%N 4
%@ 1860-2037
%F hoarau2019
%X In this paper, we describe a framework focused on spectral images rendering. The rendering of a such image leads us to three major issues: the computation time, the footprint of the spectral image, and the memory consumption of the algorithm. The computation time can be drastically reduced by the use of GPUs, however, their memory capacity and bandwidth are limited. When the spectral dimension of the image will raise, the straightforward approach of the Path Tracing will lead us to high memory consumption and latency problems. To overcome these problems, we propose the DPEPT (Deferred Path Evaluation Path Tracing) which consists in decoupling the path evaluation from the path generation. This technique reduces the memory latency and consumption of the Path Tracing. It allows us to use an efficient wavelength samples batches parallelization pattern to optimize the path evaluation step and outperforms the straightforward approach.
%L 004
%K GPU Computing
%K Global illumination
%K Predictive Rendering
%K Spectral Image Rendering
%R 10.48663/1860-2037/15.2018.4
%U http://nbn-resolving.de/urn:nbn:de:0009-6-48850
%U http://dx.doi.org/10.48663/1860-2037/15.2018.4
Download

Bibtex

@Article{hoarau2019,
  author = 	"Hoarau, Romain
		and Coiro, Eric
		and Thon, S{\'e}bastien
		and Raffin, Romain",
  title = 	"Interactive Hyper Spectral Image Rendering on GPU",
  journal = 	"Journal of Virtual Reality and Broadcasting",
  year = 	"2019",
  volume = 	"15(2018)",
  number = 	"4",
  keywords = 	"GPU Computing; Global illumination; Predictive Rendering; Spectral Image Rendering",
  abstract = 	"In this paper, we describe a framework focused on spectral images rendering. The rendering of a such image leads us to three major issues: the computation time, the footprint of the spectral image, and the memory consumption of the algorithm. The computation time can be drastically reduced by the use of GPUs, however, their memory capacity and bandwidth are limited. When the spectral dimension of the image will raise, the straightforward approach of the Path Tracing will lead us to high memory consumption and latency problems. To overcome these problems, we propose the DPEPT (Deferred Path Evaluation Path Tracing) which consists in decoupling the path evaluation from the path generation. This technique reduces the memory latency and consumption of the Path Tracing. It allows us to use an efficient wavelength samples batches parallelization pattern to optimize the path evaluation step and outperforms the straightforward approach.",
  issn = 	"1860-2037",
  doi = 	"10.48663/1860-2037/15.2018.4",
  url = 	"http://nbn-resolving.de/urn:nbn:de:0009-6-48850"
}
Download

RIS

TY  - JOUR
AU  - Hoarau, Romain
AU  - Coiro, Eric
AU  - Thon, Sébastien
AU  - Raffin, Romain
PY  - 2019
DA  - 2019//
TI  - Interactive Hyper Spectral Image Rendering on GPU
JO  - Journal of Virtual Reality and Broadcasting
VL  - 15(2018)
IS  - 4
KW  - GPU Computing
KW  - Global illumination
KW  - Predictive Rendering
KW  - Spectral Image Rendering
AB  - In this paper, we describe a framework focused on spectral images rendering. The rendering of a such image leads us to three major issues: the computation time, the footprint of the spectral image, and the memory consumption of the algorithm. The computation time can be drastically reduced by the use of GPUs, however, their memory capacity and bandwidth are limited. When the spectral dimension of the image will raise, the straightforward approach of the Path Tracing will lead us to high memory consumption and latency problems. To overcome these problems, we propose the DPEPT (Deferred Path Evaluation Path Tracing) which consists in decoupling the path evaluation from the path generation. This technique reduces the memory latency and consumption of the Path Tracing. It allows us to use an efficient wavelength samples batches parallelization pattern to optimize the path evaluation step and outperforms the straightforward approach.
SN  - 1860-2037
UR  - http://nbn-resolving.de/urn:nbn:de:0009-6-48850
DO  - 10.48663/1860-2037/15.2018.4
ID  - hoarau2019
ER  -
Download

Wordbib

<?xml version="1.0" encoding="UTF-8"?>
<b:Sources SelectedStyle="" xmlns:b="http://schemas.openxmlformats.org/officeDocument/2006/bibliography"  xmlns="http://schemas.openxmlformats.org/officeDocument/2006/bibliography" >
<b:Source>
<b:Tag>hoarau2019</b:Tag>
<b:SourceType>ArticleInAPeriodical</b:SourceType>
<b:Year>2019</b:Year>
<b:PeriodicalTitle>Journal of Virtual Reality and Broadcasting</b:PeriodicalTitle>
<b:Volume>15(2018)</b:Volume>
<b:Issue>4</b:Issue>
<b:Url>http://nbn-resolving.de/urn:nbn:de:0009-6-48850</b:Url>
<b:Url>http://dx.doi.org/10.48663/1860-2037/15.2018.4</b:Url>
<b:Author>
<b:Author><b:NameList>
<b:Person><b:Last>Hoarau</b:Last><b:First>Romain</b:First></b:Person>
<b:Person><b:Last>Coiro</b:Last><b:First>Eric</b:First></b:Person>
<b:Person><b:Last>Thon</b:Last><b:First>Sébastien</b:First></b:Person>
<b:Person><b:Last>Raffin</b:Last><b:First>Romain</b:First></b:Person>
</b:NameList></b:Author>
</b:Author>
<b:Title>Interactive Hyper Spectral Image Rendering on GPU</b:Title>
<b:Comments>In this paper, we describe a framework focused on spectral images rendering. The rendering of a such image leads us to three major issues: the computation time, the footprint of the spectral image, and the memory consumption of the algorithm. The computation time can be drastically reduced by the use of GPUs, however, their memory capacity and bandwidth are limited. When the spectral dimension of the image will raise, the straightforward approach of the Path Tracing will lead us to high memory consumption and latency problems. To overcome these problems, we propose the DPEPT (Deferred Path Evaluation Path Tracing) which consists in decoupling the path evaluation from the path generation. This technique reduces the memory latency and consumption of the Path Tracing. It allows us to use an efficient wavelength samples batches parallelization pattern to optimize the path evaluation step and outperforms the straightforward approach.</b:Comments>
</b:Source>
</b:Sources>
Download

ISI

PT Journal
AU Hoarau, R
   Coiro, E
   Thon, S
   Raffin, R
TI Interactive Hyper Spectral Image Rendering on GPU
SO Journal of Virtual Reality and Broadcasting
PY 2019
VL 15(2018)
IS 4
DI 10.48663/1860-2037/15.2018.4
DE GPU Computing; Global illumination; Predictive Rendering; Spectral Image Rendering
AB In this paper, we describe a framework focused on spectral images rendering. The rendering of a such image leads us to three major issues: the computation time, the footprint of the spectral image, and the memory consumption of the algorithm. The computation time can be drastically reduced by the use of GPUs, however, their memory capacity and bandwidth are limited. When the spectral dimension of the image will raise, the straightforward approach of the Path Tracing will lead us to high memory consumption and latency problems. To overcome these problems, we propose the DPEPT (Deferred Path Evaluation Path Tracing) which consists in decoupling the path evaluation from the path generation. This technique reduces the memory latency and consumption of the Path Tracing. It allows us to use an efficient wavelength samples batches parallelization pattern to optimize the path evaluation step and outperforms the straightforward approach.
ER
Download

Mods

<mods>
  <titleInfo>
    <title>Interactive Hyper Spectral Image Rendering on GPU</title>
  </titleInfo>
  <name type="personal">
    <namePart type="family">Hoarau</namePart>
    <namePart type="given">Romain</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Coiro</namePart>
    <namePart type="given">Eric</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Thon</namePart>
    <namePart type="given">Sébastien</namePart>
  </name>
  <name type="personal">
    <namePart type="family">Raffin</namePart>
    <namePart type="given">Romain</namePart>
  </name>
  <abstract>In this paper, we describe a framework focused on spectral images rendering. The rendering of a such image leads us to three major issues: the computation time, the footprint of the spectral image, and the memory consumption of the algorithm. The computation time can be drastically reduced by the use of GPUs, however, their memory capacity and bandwidth are limited. When the spectral dimension of the image will raise, the straightforward approach of the Path Tracing will lead us to high memory consumption and latency problems. To overcome these problems, we propose the DPEPT (Deferred Path Evaluation Path Tracing) which consists in decoupling the path evaluation from the path generation. This technique reduces the memory latency and consumption of the Path Tracing. It allows us to use an efficient wavelength samples batches parallelization pattern to optimize the path evaluation step and outperforms the straightforward approach.</abstract>
  <subject>
    <topic>GPU Computing</topic>
    <topic>Global illumination</topic>
    <topic>Predictive Rendering</topic>
    <topic>Spectral Image Rendering</topic>
  </subject>
  <classification authority="ddc">004</classification>
  <relatedItem type="host">
    <genre authority="marcgt">periodical</genre>
    <genre>academic journal</genre>
    <titleInfo>
      <title>Journal of Virtual Reality and Broadcasting</title>
    </titleInfo>
    <part>
      <detail type="volume">
        <number>15(2018)</number>
      </detail>
      <detail type="issue">
        <number>4</number>
      </detail>
      <date>2019</date>
    </part>
  </relatedItem>
  <identifier type="issn">1860-2037</identifier>
  <identifier type="urn">urn:nbn:de:0009-6-48850</identifier>
  <identifier type="doi">10.48663/1860-2037/15.2018.4</identifier>
  <identifier type="uri">http://nbn-resolving.de/urn:nbn:de:0009-6-48850</identifier>
  <identifier type="citekey">hoarau2019</identifier>
</mods>
Download

Full Metadata

Bibliographic Citation JVRB, 15(2018), no. 4.
Title

Interactive Hyper Spectral Image Rendering on GPU (eng)
Author Romain Hoarau, Eric Coiro, Sébastien Thon, Romain Raffin
Language eng
Abstract In this paper, we describe a framework focused on spectral images rendering. The rendering of a such image leads us to three major issues: the computation time, the footprint of the spectral image, and the memory consumption of the algorithm. The computation time can be drastically reduced by the use of GPUs, however, their memory capacity and bandwidth are limited. When the spectral dimension of the image will raise, the straightforward approach of the Path Tracing will lead us to high memory consumption and latency problems. To overcome these problems, we propose the DPEPT (Deferred Path Evaluation Path Tracing) which consists in decoupling the path evaluation from the path generation. This technique reduces the memory latency and consumption of the Path Tracing. It allows us to use an efficient wavelength samples batches parallelization pattern to optimize the path evaluation step and outperforms the straightforward approach.
Subject GPU Computing, Global illumination, Predictive Rendering, Spectral Image Rendering
Classified Subjects
swd
  • 7518941-0, Globale Beleuchtung
  • 4582114-8, Grafikprozessor
  • 4219666-8, Rendering
DDC 004
Rights DPPL
URN: urn:nbn:de:0009-6-48850
DOI https://doi.org/10.48663/1860-2037/15.2018.4