arrow
返回

Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets

delete2017-10-01
delete26
delete
OA
AI
L
Linlin Yang
C
Ce Li
韩
韩军功 (Jungong Han)
C
Chen Chen
Qixiang Ye 封面图
Qixiang Ye (Qixiang Ye)
张
张宝昌 (Baochang Zhang) *
X
Xianbin Cao
W
Wanquan Liu
DOI:10.1109/JSTSP.2017.2743683delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Convolution sparse coding (CSC) has attracted much attention recently due to its advantages in image reconstruction and enhancement. However, the coding process suffers from perturbations caused by variations of input samples, as the consistence of features from similar input samples are not well addressed in the existing literature. In this paper, we will tackle this feature consistence problem from a set of samples via a proposed manifold constrained convolutional sparse coding (MCSC) method. The core idea of MCSC is to use the intrinsic manifold (Laplacian) structure of the input data to regularize the traditional CSC such that the consistence between features extracted from input samples can be well preserved. To implement the proposed MCSC method efficiently, the alternating direction method of multipliers (ADMM) approach is employed, which can consistently integrate the underlying Laplacian constraints during the optimization process. With this regularized data structure constraint, the MCSC can achieve a much better solution which is robust to the variance of the input samples against overcomplete filters. We demonstrate the capacity of MCSC by providing the state-of-the-art results when applied it to the task of reconstructing light fields. Finally, we show that the proposed MCSC is a generic approach as it also achieves better results than the state-of-the-art approaches based on convolutional sparse coding in other image reconstruction tasks, such as face reconstruction, digit reconstruction, and image restoration.
Keyword:
Convolutional sparse coding
image reconstruction
image deblurring
light field
manifold constrained convolutional sparse coding
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Journal of Selected Topics in Signal Processing 封面图
IEEE Journal of Selected Topics in Signal Processing
IF:
13.7
论文数:
1.9K
被引数:
1.1W

机构

U
university of chinese academy of sciences, cas
学者数:
4.1W
论文数: 3.8W
被引数: 75
B
Beihang University
学者数:
5.2W
论文数: 4.1W
被引数: 37
State University System of Florida 封面图
State University System of Florida
学者数:
12.8W
论文数: 10.9W
被引数: 130
L
Lancaster University
学者数:
9.5K
论文数: 1.1W
被引数: 1.7W
U
University of Central Florida
学者数:
8.7K
论文数: 6.8K
被引数: 1.4W
C
chinese academy of sciences
学者数:
56.7W
论文数: 45.0W
被引数: 704
学者 查看更多机构
引用论文

引用论文

Near infrared photoluminescence in Zn1–xNixS
err2009-05-07
err0
PREAI
errN. V. Joshi; Jorge Luengo; Fatima Vera
err分享
err收藏
Ultrasonography of the uterus of the goat
err1994-03-01
err0
errOAAI
errJ.W. Hesselink; M.A.M. Taverne
err分享
err收藏
err分享
err收藏
The behavioral, psychological, and social impacts of team sports: a systematic review and meta-analysis
err2020-12-16
err0
PREAI
errScott L. Zuckerman; Alan R. Tang; Kelsey E. Richard; Candace J. Grisham; Andrew W. Kuhn; Christopher M. Bonfield; Aaron M. Yengo-Kahn
err分享
err收藏
学者 查看更多内容