Fast closed-form matting using a hierarchical data structure

Chunxia Xiao, Meng Liu, Donglin Xiao, Zhao Dong, Kwan-Liu Ma

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Image/video matting is one of the key operations in many image/video editing applications. Although previous methods can generate high-quality matting results, their high computational cost in processing high-resolution image and video data often limits their usability. In this paper, we present a unified acceleration method for closed-form image and video matting using a hierarchical data structure, which achieves an excellent compromise between quality and speed. We first apply a Gaussian KD tree to adaptively cluster the input high-dimensional image and video feature space into a low-dimensional feature space. Then, we solve the affinity-weighted Laplacian alpha matting in the reduced feature space. The final matting results are derived using detail-aware alpha interpolation. Our algorithm can be fully parallelized by exploiting advanced graphics hardware, which can further accelerate the matting computation. Our method accelerates existing methods by at least an order of magnitude with good quality, and also greatly reduces the memory consumption. This acceleration strategy is also extended to support other affinity-based matting approaches, which makes it a more general accelerating framework for a variety of matting methods. Finally, we apply the presented method to accelerate image and video dehazing, and image shadow detection and removal.

Original languageEnglish (US)
Article number6574248
Pages (from-to)49-62
Number of pages14
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume24
Issue number1
DOIs
StatePublished - Jan 1 2014

Fingerprint

Data structures
Image resolution
Interpolation
Hardware
Data storage equipment
Processing
Costs

Keywords

  • Acceleration
  • dehazing
  • Gaussian KD tree
  • GPU
  • matting

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

Fast closed-form matting using a hierarchical data structure. / Xiao, Chunxia; Liu, Meng; Xiao, Donglin; Dong, Zhao; Ma, Kwan-Liu.

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 24, No. 1, 6574248, 01.01.2014, p. 49-62.

Research output: Contribution to journalArticle

Xiao, Chunxia ; Liu, Meng ; Xiao, Donglin ; Dong, Zhao ; Ma, Kwan-Liu. / Fast closed-form matting using a hierarchical data structure. In: IEEE Transactions on Circuits and Systems for Video Technology. 2014 ; Vol. 24, No. 1. pp. 49-62.
@article{b43a051a80844459b703067206b8977d,
title = "Fast closed-form matting using a hierarchical data structure",
abstract = "Image/video matting is one of the key operations in many image/video editing applications. Although previous methods can generate high-quality matting results, their high computational cost in processing high-resolution image and video data often limits their usability. In this paper, we present a unified acceleration method for closed-form image and video matting using a hierarchical data structure, which achieves an excellent compromise between quality and speed. We first apply a Gaussian KD tree to adaptively cluster the input high-dimensional image and video feature space into a low-dimensional feature space. Then, we solve the affinity-weighted Laplacian alpha matting in the reduced feature space. The final matting results are derived using detail-aware alpha interpolation. Our algorithm can be fully parallelized by exploiting advanced graphics hardware, which can further accelerate the matting computation. Our method accelerates existing methods by at least an order of magnitude with good quality, and also greatly reduces the memory consumption. This acceleration strategy is also extended to support other affinity-based matting approaches, which makes it a more general accelerating framework for a variety of matting methods. Finally, we apply the presented method to accelerate image and video dehazing, and image shadow detection and removal.",
keywords = "Acceleration, dehazing, Gaussian KD tree, GPU, matting",
author = "Chunxia Xiao and Meng Liu and Donglin Xiao and Zhao Dong and Kwan-Liu Ma",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/TCSVT.2013.2276153",
language = "English (US)",
volume = "24",
pages = "49--62",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - Fast closed-form matting using a hierarchical data structure

AU - Xiao, Chunxia

AU - Liu, Meng

AU - Xiao, Donglin

AU - Dong, Zhao

AU - Ma, Kwan-Liu

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Image/video matting is one of the key operations in many image/video editing applications. Although previous methods can generate high-quality matting results, their high computational cost in processing high-resolution image and video data often limits their usability. In this paper, we present a unified acceleration method for closed-form image and video matting using a hierarchical data structure, which achieves an excellent compromise between quality and speed. We first apply a Gaussian KD tree to adaptively cluster the input high-dimensional image and video feature space into a low-dimensional feature space. Then, we solve the affinity-weighted Laplacian alpha matting in the reduced feature space. The final matting results are derived using detail-aware alpha interpolation. Our algorithm can be fully parallelized by exploiting advanced graphics hardware, which can further accelerate the matting computation. Our method accelerates existing methods by at least an order of magnitude with good quality, and also greatly reduces the memory consumption. This acceleration strategy is also extended to support other affinity-based matting approaches, which makes it a more general accelerating framework for a variety of matting methods. Finally, we apply the presented method to accelerate image and video dehazing, and image shadow detection and removal.

AB - Image/video matting is one of the key operations in many image/video editing applications. Although previous methods can generate high-quality matting results, their high computational cost in processing high-resolution image and video data often limits their usability. In this paper, we present a unified acceleration method for closed-form image and video matting using a hierarchical data structure, which achieves an excellent compromise between quality and speed. We first apply a Gaussian KD tree to adaptively cluster the input high-dimensional image and video feature space into a low-dimensional feature space. Then, we solve the affinity-weighted Laplacian alpha matting in the reduced feature space. The final matting results are derived using detail-aware alpha interpolation. Our algorithm can be fully parallelized by exploiting advanced graphics hardware, which can further accelerate the matting computation. Our method accelerates existing methods by at least an order of magnitude with good quality, and also greatly reduces the memory consumption. This acceleration strategy is also extended to support other affinity-based matting approaches, which makes it a more general accelerating framework for a variety of matting methods. Finally, we apply the presented method to accelerate image and video dehazing, and image shadow detection and removal.

KW - Acceleration

KW - dehazing

KW - Gaussian KD tree

KW - GPU

KW - matting

UR - http://www.scopus.com/inward/record.url?scp=84892569004&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892569004&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2013.2276153

DO - 10.1109/TCSVT.2013.2276153

M3 - Article

VL - 24

SP - 49

EP - 62

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 1

M1 - 6574248

ER -