Home > Research > Publications & Outputs > Image Reconstruction via Manifold Constrained C...

Associated organisational unit

Electronic data

  • LinlinIEEESTSP

    Rights statement: ©2017 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 1.93 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Image Reconstruction via Manifold Constrained Convolutional Sparse Coding for Image Sets

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print
  • Linlin Yang
  • Ce Li
  • Jungong Han
  • Chen Chen
  • Qixiang Ye
  • Baochang Zhang
  • Xianbin Cao
  • Wanquan Liu
Close
<mark>Journal publication date</mark>1/09/2017
<mark>Journal</mark>IEEE Journal of Selected Topics in Signal Processing
Publication StatusE-pub ahead of print
Early online date1/09/17
<mark>Original language</mark>English

Abstract

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 over-complete 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.

Bibliographic note

©2017 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.