RI | Research | Projects | Texture Replacement in Real Images

Text only version of this site

Texture Replacement in Real Images Head: Yanxi Liu Contact: Yanxi Liu (yanxi@cs.cmu.edu) Mailing address: Carnegie Mellon University Robotics Institute 5000 Forbes Avenue Pittsburgh, PA 15213 Associated center: VASC Associated lab/group: Computational Symmetry For more information, see this project's homepage.

This page last updated - February 2007.

Project Description

Texture replacement in real images has many applications, such as interior design, digital movie making and computer graphics. The goal is to replace some specified texture patterns in an image while preserving lighting effects, shadows and occlusions. To achieve convincing replacement results we have to detect texture patterns and estimate lighting map from a given image. Given a sample texture patch, a standard tile is computed. Candidate texture regions are determined by mutual information between the standard tile and each image patch. Regions with high mutual information scores are used to estimate the admissible lighting distributions, which is represented by cached statistics. Spatial lighting change constraints are represented by a Markov random field model. Maximum a posteriori estimation of the texture segmentation and lighting map is solved in a stochastic annealing fashion, namely, the Markov Chain Monte Carlo method. Visually satisfactory result is achieved using this statistical sampling model.

Personnel [Past Members]

	Name	Title	Email Address
	Yanxi Liu	Adjunct Associate Research Professor	yanxi@cs.cmu.edu

Current Sub-projects

Texture Synthesis on Near-regular Patterns - We are developing near regular texture synthesis algorithms for improved natural appearances.

Publications

Note: This list may not be comprehensive. It contains only those publications in the RI publications database. Entries are listed in reverse chronological order.

• Texture Replacement in Real Images
  Y. Tsin, Y. Liu, and V. Ramesh
  IEEE Conference on Computer Vision and Pattern Recognition, Vol. 2, December, 2001, pp. 539 = 544. [Abstract]
  Download: pdf [731 KB], ps.gz [7075 KB] copyrighted