A shape enhancement technique based on multi-channel salience measure

Authors:
Yongwei Miao;Jieqing Feng;Jinrong Wang;Renato Pajarola
Affiliations:
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China;State Key Lab. of CAD&CG, Zhejiang University, Hangzhou, China;State Key Lab. of CAD&CG, Zhejiang University, Hangzhou, China;Department of Informatics, University of Zürich, Zürich, Switzerland
Venue:
CVM'12 Proceedings of the First international conference on Computational Visual Media
Year:
2012

Citing 14
Cited 0

A Model of Saliency-Based Visual Attention for Rapid Scene Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Digital Image Processing

Digital Image Processing
Shade trees

SIGGRAPH '84 Proceedings of the 11th annual conference on Computer graphics and interactive techniques
Estimating the tensor of curvature of a surface from a polyhedral approximation

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
View-dependent displacement mapping

ACM SIGGRAPH 2003 Papers
Guest Editors' Introduction: Smart Depiction for Visual Communication

IEEE Computer Graphics and Applications
Mesh saliency

ACM SIGGRAPH 2005 Papers
Exaggerated shading for depicting shape and detail

ACM SIGGRAPH 2006 Papers
Saliency-guided Enhancement for Volume Visualization

IEEE Transactions on Visualization and Computer Graphics
Importance-Driven Focus of Attention

IEEE Transactions on Visualization and Computer Graphics
Geometric modeling based on polygonal meshes Video files associated with this course are available from the citation page

ACM SIGGRAPH 2007 courses
Persuading Visual Attention through Geometry

IEEE Transactions on Visualization and Computer Graphics
Relief analysis and extraction

ACM SIGGRAPH Asia 2009 papers
Technical Section: A simple normal enhancement technique for interactive non-photorealistic renderings

Computers and Graphics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we develop a novel visual saliency based shape enhancement technique for relief surfaces. It consists of three steps. Firstly, we calculate the multi-channel salience map of the underlying shape by combining three feature maps, i.e., the feature map of local height distribution, normal difference, and mean curvature variation. Secondly, we manipulate the original relief surface by a salience-domain shape manipulation function. Finally, we adjust surface normals of the original shape as the corresponding final normals of the manipulated surface. The experimental results show that our proposed algorithm can adjust the shading of the original shape and thus for improving its shape depiction.