Gyroscope-Aided Motion Deblurring with Deep Networks
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00334770" target="_blank" >RIV/68407700:21230/19:00334770 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1109/WACV.2019.00208" target="_blank" >http://dx.doi.org/10.1109/WACV.2019.00208</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/WACV.2019.00208" target="_blank" >10.1109/WACV.2019.00208</a>
Alternative languages
Result language
angličtina
Original language name
Gyroscope-Aided Motion Deblurring with Deep Networks
Original language description
We propose a deblurring method that incorporates gyroscope measurements into a convolutional neural network (CNN). With the help of such measurements, it can handle extremely strong and spatially-variant motion blur. At the same time, the image data is used to overcome the limitations of gyro-based blur estimation. To train our network, we also introduce a novel way of generating realistic training data using the gyroscope. The evaluation shows a clear improvement in visual quality over the state-of-the-art while achieving real-time performance. Furthermore, the method is shown to improve the performance of existing feature detectors and descriptors against the motion blur.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION
ISBN
978-1-7281-1975-5
ISSN
2472-6737
e-ISSN
—
Number of pages
9
Pages from-to
1914-1922
Publisher name
IEEE
Place of publication
NEW YORK, NY
Event location
Waikoloa Village
Event date
Jan 7, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000469423400200