Título:
Deep video deblurring for hand-held cameras
Otros títulos:
Coordinador:
Director:
Compilador:
Autor:
Su, Shuochen
Delbracio, Mauricio
Wang, Jue
Sapiro, Guillermo
Heidrich, Wolfgang
Wang, Oliver
Delbracio, Mauricio
Wang, Jue
Sapiro, Guillermo
Heidrich, Wolfgang
Wang, Oliver
Tutor:
Tipo de documento:
Ponencia
Editor:
Palabras clave:
Adaptive optics
Optical imaging
Cameras
Data models
Optical imaging
Cameras
Data models
Descriptores:
Procesamiento de Señales
Año de publicación:
2017
Contenido:
Resumen:
Motion blur from camera shake is a major problem in videos captured by hand-held devices. Unlike single-image deblurring, video-based approaches can take advantage of the abundant information that exists across neighboring frames. As a result the best performing methods rely on the alignment of nearby frames. However, aligning images is a computationally expensive and fragile procedure, and methods that aggregate information must therefore be able to identify which regions have been accurately aligned and which have not, a task that requires high level scene understanding. In this work, we introduce a deep learning solution to video deblurring, where a CNN is trained end-toend to learn how to accumulate information across frames. To train this network, we collected a dataset of real videos recorded with a high frame rate camera, which we use to generate synthetic motion blur for supervision. We show that the features learned from this dataset extend to deblurring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a number of other baselines
Descripción:
Versión de acceso abierto disponibilizada por Computer Vision Foundation
metadata.articulos.dc.description.uri:
Editorial:
EN:
Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21-16 jul. 2017
Financiadores:
Citación:
Su, S, Delbracio, M, Wang, J, Sapiro, G, Heidrich, W, Wang, O. "Deep Video Deblurring for Hand-Held Cameras" Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017.
Citación:
metadata.articulos.cc.license.name:
ISBN:
e-ISBN:
ISSN:
ISMN:
Otros identificadores:
Cobertura geográfica:
Cobertura temporal:
Departamento académico:
Procesamiento de Señales
Grupo de investigación:
Tratamiento de Imágenes
Licencia:
Licencia Creative Commons Atribución - No Comercial - Sin Derivadas (CC - By-NC-ND 4.0)
Colecciones:
| Ficheros | Descripción | Tamaño | Formato | ||
|---|---|---|---|---|---|
| SDWSHW17.pdf | — | 7.92 MB | Adobe PDF |