Mixed-Domain Edge-Aware Image Manipulation

 

Xian-Ying Li1   Yan Gu1   Shi-Min Hu1   Ralph R. Martin2

 

1Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing

2School of Computer Science & Informatics, Cardiff University, Wales

 

 

 

 

 

Abstract

 

This paper gives a novel approach to edge-aware image manipulation. Our method processes a Gaussian pyramid from coarse to fine, and at each level, applies a nonlinear filter bank to the neighborhood of each pixel. Outputs of these spatially-varying filters are merged using global optimization. The optimization problem is solved using an explicit mixeddomain (real space and DCT transform space) solution, which is efficient, accurate, and easy-to-implement. We demonstrate applications of our method to a set of problems including detail and contrast manipulation, HDR compression, non-photorealistic rendering, and haze removal.

 

 

Paper

 

Mixed-Domain Edge-Aware Image Manipulation [7.0M Paper]

Xian-Ying Li, Yan Gu, Ralph R. Martin, and Shi-Min Hu.

IEEE Transactions on Image Processing, 2013, 22(5), 1915-1925.

 

 

BibTex

 

@article {li2013mixed,
  author = {Li, Xian-Ying and Gu, Yan and Hu, Shi-Min and Ralph R. Martin},
  title = {Mixed-Domain Edge-Aware Image Manipulation},
  journal = {IEEE Transactions on Image Processing},
  year = {2013},
  volume = {22},
  number = {5},
  pages = {1915-1925},
}

 

 

 

Software

 

MixedDomainFilter (C++ Code)