Video Super-Resolution via Deep Draft-Ensemble Learning

We propose a new direction for fast video super-resolution (VideoSR) via a SR draft ensemble, which is defined as the set of high-resolution patch candidates before final image deconvolution. Our method contains two main components -- i.e., SR draft ensemble generation and its optimal reconstruction...

Full description

Saved in:
Bibliographic Details
Published in2015 IEEE International Conference on Computer Vision (ICCV) pp. 531 - 539
Main Authors Liao, Renjie, Tao, Xin, Li, Ruiyu, Ma, Ziyang, Jia, Jiaya
Format Conference Proceeding Journal Article
LanguageEnglish
Published IEEE 01.12.2015
Subjects
Computer vision
Conferences
Deconvolution
Feedforward
Feedforward neural networks
Image reconstruction
Image resolution
Kernel
Learning
Motion estimation
Neural networks
Optical imaging
Optimization
Pipelines
Reconstruction
Online AccessGet full text

Cover

More Information
Summary:We propose a new direction for fast video super-resolution (VideoSR) via a SR draft ensemble, which is defined as the set of high-resolution patch candidates before final image deconvolution. Our method contains two main components -- i.e., SR draft ensemble generation and its optimal reconstruction. The first component is to renovate traditional feedforward reconstruction pipeline and greatly enhance its ability to compute different super resolution results considering large motion variation and possible errors arising in this process. Then we combine SR drafts through the nonlinear process in a deep convolutional neural network (CNN). We analyze why this framework is proposed and explain its unique advantages compared to previous iterative methods to update different modules in passes. Promising experimental results are shown on natural video sequences.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:2380-7504
DOI:10.1109/ICCV.2015.68