English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 DetailsSummary
  Spatio-Temporal Upsampling on the GPU

Herzog, R., Eisemann, E., Myszkowski, K., & Seidel, H.-P. (2010). Spatio-Temporal Upsampling on the GPU. In A. Varshney, C. Wyman, D. Aliaga, & M. M. Oliveira (Eds.), Proceedings I3D 2010 (pp. 91-98). New York, NY: ACM.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-178C-C Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0029-CD1E-D
Genre: Conference Paper
Latex : Spatio-Temporal Upsampling on the {GPU}

Files

show Files
hide Files
:
Herzog2010i3D.pdf (Any fulltext), 12MB
 
File Permalink:
-
Name:
Herzog2010i3D.pdf
Description:
-
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-
:
spatioTemporalUpsampling_preprintI3D2010.pdf (Preprint), 12MB
 
File Permalink:
-
Name:
spatioTemporalUpsampling_preprintI3D2010.pdf
Description:
-
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Herzog, Robert1, Author           
Eisemann, Elmar1, Author           
Myszkowski, Karol1, Author           
Seidel, Hans-Peter1, Author           
Affiliations:
1Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              

Content

show
hide
Free keywords: -
 Abstract: Pixel processing is becoming increasingly expensive for real-time applications due to the complexity of today's shaders and high-resolution framebuffers. However, most shading results are spatially or temporally coherent, which allows for sparse sampling and reuse of neighboring pixel values. This paper proposes a simple framework for spatio-temporal upsampling on modern GPUs. In contrast to previous work, which focuses either on temporal or spatial processing on the GPU, we exploit coherence in both. Our algorithm combines adaptive motion-compensated filtering over time and geometry-aware upsampling in image space. It is robust with respect to high-frequency temporal changes, and achieves substantial performance improvements by limiting the number of recomputed samples per frame. At the same time, we increase the quality of spatial upsampling by recovering missing information from previous frames. This temporal strategy also allows us to ensure that the image converges to a higher quality result.

Details

show
hide
Language(s): eng - English
 Dates: 2011-01-212010
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: eDoc: 537285
DOI: 10.1145/1730804.1730819
BibTex Citekey: HerzogI3D2010
 Degree: -

Event

show
hide
Title: ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games
Place of Event: Washington DC, USA
Start-/End Date: 2010-02-19 - 2010-02-21

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings I3D 2010
  Abbreviation : I3D 2010
  Subtitle : ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games
Source Genre: Proceedings
 Creator(s):
Varshney, Amitabh1, Editor
Wyman, Chris1, Editor
Aliaga, Daniel1, Editor
Oliveira, Manuel M.1, Editor
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: New York, NY : ACM
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 91 - 98 Identifier: ISBN: 978-1-60558-939-8