Image and video restorations via nonlocal kernel regression

Haichao Zhang, Jianchao Yang, Yanning Zhang, Thomas S. Huang

Research output: Contribution to journalArticlepeer-review

Abstract

A nonlocal kernel regression (NL-KR) model is presented in this paper for various image and video restoration tasks. The proposed method exploits both the nonlocal self-similarity and local structural regularity properties in natural images. The nonlocal self-similarity is based on the observation that image patches tend to repeat themselves in natural images and videos, and the local structural regularity observes that image patches have regular structures where accurate estimation of pixel values via regression is possible. By unifying both properties explicitly, the proposed NL-KR framework is more robust in image estimation, and the algorithm is applicable to various image and video restoration tasks. In this paper, we apply the proposed model to image and video denoising, deblurring, and superresolution reconstruction. Extensive experimental results on both single images and realistic video sequences demonstrate that the proposed framework performs favorably with previous works both qualitatively and quantitatively.

Original languageEnglish (US)
Pages (from-to)1035-1046
Number of pages12
JournalIEEE Transactions on Cybernetics
Volume43
Issue number3
DOIs
StatePublished - Jun 1 2013

Keywords

  • Deblurring
  • Denoising
  • Local structural regression
  • Nonlocal self-similarity
  • Restoration
  • Superresolution (SR)

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Information Systems
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Image and video restorations via nonlocal kernel regression'. Together they form a unique fingerprint.

Cite this