Handle URI:
http://hdl.handle.net/10754/623957
Title:
Consensus Convolutional Sparse Coding
Authors:
Choudhury, Biswarup; Swanson, Robin; Heide, Felix; Wetzstein, Gordon; Heidrich, Wolfgang ( 0000-0002-4227-8508 )
Abstract:
Convolutional sparse coding (CSC) is a promising direction for unsupervised learning in computer vision. In contrast to recent supervised methods, CSC allows for convolutional image representations to be learned that are equally useful for high-level vision tasks and low-level image reconstruction and can be applied to a wide range of tasks without problem-specific retraining. Due to their extreme memory requirements, however, existing CSC solvers have so far been limited to low-dimensional problems and datasets using a handful of low-resolution example images at a time. In this paper, we propose a new approach to solving CSC as a consensus optimization problem, which lifts these limitations. By learning CSC features from large-scale image datasets for the first time, we achieve significant quality improvements in a number of imaging tasks. Moreover, the proposed method enables new applications in high dimensional feature learning that has been intractable using existing CSC methods. This is demonstrated for a variety of reconstruction problems across diverse problem domains, including 3D multispectral demosaickingand 4D light field view synthesis.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Conference/Event name:
KAUST Research Conference 2017: Visual Computing – Modeling and Reconstruction
Issue Date:
11-Apr-2017
Type:
Poster
Appears in Collections:
Posters; KAUST Research Conference 2017: Visual Computing – Modeling and Reconstruction

Full metadata record

DC FieldValue Language
dc.contributor.authorChoudhury, Biswarupen
dc.contributor.authorSwanson, Robinen
dc.contributor.authorHeide, Felixen
dc.contributor.authorWetzstein, Gordonen
dc.contributor.authorHeidrich, Wolfgangen
dc.date.accessioned2017-05-31T11:53:47Z-
dc.date.available2017-05-31T11:53:47Z-
dc.date.issued2017-04-11-
dc.identifier.urihttp://hdl.handle.net/10754/623957-
dc.description.abstractConvolutional sparse coding (CSC) is a promising direction for unsupervised learning in computer vision. In contrast to recent supervised methods, CSC allows for convolutional image representations to be learned that are equally useful for high-level vision tasks and low-level image reconstruction and can be applied to a wide range of tasks without problem-specific retraining. Due to their extreme memory requirements, however, existing CSC solvers have so far been limited to low-dimensional problems and datasets using a handful of low-resolution example images at a time. In this paper, we propose a new approach to solving CSC as a consensus optimization problem, which lifts these limitations. By learning CSC features from large-scale image datasets for the first time, we achieve significant quality improvements in a number of imaging tasks. Moreover, the proposed method enables new applications in high dimensional feature learning that has been intractable using existing CSC methods. This is demonstrated for a variety of reconstruction problems across diverse problem domains, including 3D multispectral demosaickingand 4D light field view synthesis.en
dc.titleConsensus Convolutional Sparse Codingen
dc.typePosteren
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.conference.dateApril 10-12, 2017en
dc.conference.nameKAUST Research Conference 2017: Visual Computing – Modeling and Reconstructionen
dc.conference.locationKAUSTen
dc.contributor.institutionUniversity of Torontoen
dc.contributor.institutionStanford Universityen
kaust.authorChoudhury, Biswarupen
kaust.authorHeidrich, Wolfgangen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.