FlexISP: a flexible camera image processing framework

Handle URI:
http://hdl.handle.net/10754/556541
Title:
FlexISP: a flexible camera image processing framework
Authors:
Heide, Felix; Egiazarian, Karen; Kautz, Jan; Pulli, Kari; Steinberger, Markus; Tsai, Yun-Ta; Rouf, Mushfiqur; Pająk, Dawid; Reddy, Dikpal; Gallo, Orazio; Liu, Jing; Heidrich, Wolfgang ( 0000-0002-4227-8508 )
Abstract:
Conventional pipelines for capturing, displaying, and storing images are usually defined as a series of cascaded modules, each responsible for addressing a particular problem. While this divide-and-conquer approach offers many benefits, it also introduces a cumulative error, as each step in the pipeline only considers the output of the previous step, not the original sensor data. We propose an end-to-end system that is aware of the camera and image model, enforces natural-image priors, while jointly accounting for common image processing steps like demosaicking, denoising, deconvolution, and so forth, all directly in a given output representation (e.g., YUV, DCT). Our system is flexible and we demonstrate it on regular Bayer images as well as images from custom sensors. In all cases, we achieve large improvements in image quality and signal reconstruction compared to state-of-the-art techniques. Finally, we show that our approach is capable of very efficiently handling high-resolution images, making even mobile implementations feasible.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
FlexISP: a flexible camera image processing framework, 2014, 33 (6):1 ACM Transactions on Graphics
Publisher:
Association for Computing Machinery (ACM)
Journal:
ACM Transactions on Graphics
Issue Date:
19-Nov-2014
DOI:
10.1145/2661229.2661260
Type:
Article
ISSN:
07300301
Additional Links:
http://dl.acm.org/citation.cfm?doid=2661229.2661260
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorHeide, Felixen
dc.contributor.authorEgiazarian, Karenen
dc.contributor.authorKautz, Janen
dc.contributor.authorPulli, Karien
dc.contributor.authorSteinberger, Markusen
dc.contributor.authorTsai, Yun-Taen
dc.contributor.authorRouf, Mushfiquren
dc.contributor.authorPająk, Dawiden
dc.contributor.authorReddy, Dikpalen
dc.contributor.authorGallo, Orazioen
dc.contributor.authorLiu, Jingen
dc.contributor.authorHeidrich, Wolfgangen
dc.date.accessioned2015-06-07T22:06:46Zen
dc.date.available2015-06-07T22:06:46Zen
dc.date.issued2014-11-19en
dc.identifier.citationFlexISP: a flexible camera image processing framework, 2014, 33 (6):1 ACM Transactions on Graphicsen
dc.identifier.issn07300301en
dc.identifier.doi10.1145/2661229.2661260en
dc.identifier.urihttp://hdl.handle.net/10754/556541en
dc.description.abstractConventional pipelines for capturing, displaying, and storing images are usually defined as a series of cascaded modules, each responsible for addressing a particular problem. While this divide-and-conquer approach offers many benefits, it also introduces a cumulative error, as each step in the pipeline only considers the output of the previous step, not the original sensor data. We propose an end-to-end system that is aware of the camera and image model, enforces natural-image priors, while jointly accounting for common image processing steps like demosaicking, denoising, deconvolution, and so forth, all directly in a given output representation (e.g., YUV, DCT). Our system is flexible and we demonstrate it on regular Bayer images as well as images from custom sensors. In all cases, we achieve large improvements in image quality and signal reconstruction compared to state-of-the-art techniques. Finally, we show that our approach is capable of very efficiently handling high-resolution images, making even mobile implementations feasible.en
dc.publisherAssociation for Computing Machinery (ACM)en
dc.relation.urlhttp://dl.acm.org/citation.cfm?doid=2661229.2661260en
dc.rights© ACM, 2014. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM Transactions on Graphics, Volume 33 Issue 6, November 2014. http://doi.acm.org/10.1145/2661229.2661260en
dc.titleFlexISP: a flexible camera image processing frameworken
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalACM Transactions on Graphicsen
dc.eprint.versionPost-printen
dc.contributor.institutionNVIDIAen
dc.contributor.institutionTU Grazen
dc.contributor.institutionUBCen
dc.contributor.institutionUC Santa Cruzen
dc.contributor.institutionTUTen
kaust.authorHeidrich, Wolfgangen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.