Treffer: SSVM 2015: Scale Space and Variational Methods in Computer Vision / Artifact-free variational MPEG decompression
Title:
SSVM 2015: Scale Space and Variational Methods in Computer Vision / Artifact-free variational MPEG decompression
Authors:
Publisher Information:
2015
Document Type:
E-Ressource
Electronic Resource
Index Terms:
Availability:
Open access content. Open access content
Note:
31.80
31.76
31.48
English
31.76
31.48
English
Other Numbers:
A9G oai:unipub.uni-graz.at:3581346
eki:OBVAC15365474
urn:nbn:at:at-ubg:3-5585
https://resolver.obvsg.at/urn:nbn:at:at-ubg:3-5585
system:AC15365474
1103604244
eki:OBVAC15365474
urn:nbn:at:at-ubg:3-5585
https://resolver.obvsg.at/urn:nbn:at:at-ubg:3-5585
system:AC15365474
1103604244
Contributing Source:
UNIV OF GRAZ
From OAIster®, provided by the OCLC Cooperative.
From OAIster®, provided by the OCLC Cooperative.
Accession Number:
edsoai.on1103604244
Database:
OAIster
Weitere Informationen
We propose a variational method for artifact-free video de- compression that is capable of processing any MPEG-2 encoded movie. The method extracts, from a given MPEG-2 file, a set of admissible image sequences and minimizes an artifact-penalizing spatio-temporal regularization functional over this set, giving an optimal decompressed image sequence. For regularization, we use the infimal convolution of spatiotemporal Total Generalized Variation functionals (ICTGV). Numerical experiments on MPEG encoded files show that our approach significantly increases image quality compared to standard decompression.
(VLID)3581346