Anchored Projection Based Capped l2,1-Norm Regression for Super-Resolution

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)

1 Scopus Citations
View graph of relations

Author(s)

  • Xiaotian Ma
  • Mingbo Zhao
  • Zhao Zhang
  • Jicong Fan
  • Choujun Zhan

Related Research Unit(s)

Detail(s)

Original languageEnglish
Title of host publicationPRICAI 2018: Trends in Artificial Intelligence
Subtitle of host publication15th Pacific Rim International Conference on Artificial Intelligence, Proceedings
EditorsXin Geng, Byeong-Ho Kang
PublisherSpringer, Cham
Pages10-18
Volume2
ISBN (Electronic)978-3-319-97310-4
ISBN (Print)978-3-319-97309-8
Publication statusPublished - Aug 2018

Publication series

NameLecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence)
PublisherSpringer, Cham
VolumeLNAI 11013
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Title15th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2018
PlaceChina
CityNanjing
Period28 - 31 August 2018

Abstract

Single image super resolution task is aimed to recover a high resolution image with pleasing visual quality from a single low resolution image. It is a highly under-constrained problem because of the ambiguous mapping between low/high resolution patch domain. In order to alleviate the ambiguity problem, we split input patches into numerous subclasses and collect exemplars according to the sparse dictionary atoms. However, we observe that there still exist some similar regressors do not share the same regression in the same subclass, which may increase the super-resolving error for training data in each cluster. In this paper, we propose a robust and effective method based capped l2,1 -norm regression to address this problem. The proposed method can automatically exclude outliers in each cluster during the training phase and give the potential to learn local prior information accurately. Numerous experimental results demonstrate that the proposed algorithm achieves better reconstruction performance against other state-of-the-art methods.

Research Area(s)

  • Capped l2,1-norm regression, Local linear regression, Single image super resolution

Bibliographic Note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

Citation Format(s)

Anchored Projection Based Capped l2,1-Norm Regression for Super-Resolution. / Ma, Xiaotian; Zhao, Mingbo; Zhang, Zhao; Fan, Jicong; Zhan, Choujun.

PRICAI 2018: Trends in Artificial Intelligence: 15th Pacific Rim International Conference on Artificial Intelligence, Proceedings. ed. / Xin Geng; Byeong-Ho Kang. Vol. 2 Springer, Cham, 2018. p. 10-18 (Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence); Vol. LNAI 11013).

Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45)32_Refereed conference paper (with ISBN/ISSN)