Mesh Saliency with Global Rarity

Guo Jinliang Wu1     Xiaoyong Shen1     Wei Zhu1     Ligang Liu2 
  1Zhejiang University  
  2University of Science and Technology of China  

Graphical Models, 75(5): 255-264, 2013


Mesh saliency detection on the Lion model by our method. (a) Input mesh; (b) Saliency map using our method; (c) Saliency map using the method of Lee et al. [7]. (d-f) Geometric processing based on our saliency: mesh smoothing, mesh simplification, and mesh sampling.




Reliable estimation of visual saliency is helpful to guide many computer graphics tasks including shape matching, simplification, segmentation, etc. Inspired by basic principles induced by psychophysics studies, we propose a novel approach for computing saliency for 3D mesh surface considering both local contrast and global rarity. First, a multi-scale local shape descriptor is introduced to capture local geometric features with various regions, which is rotationally invariant. Then, we present an efficient patch-based local contrast method based on the multi-scale local descriptor. The global rarity is defined by its specialty to all other vertices. To be more efficient, we compute it on clusters first and interpolate on vertices later. Finally, our mesh saliency is obtained by the linear combination of the local contrast and the global rarity. Our method is efficient, robust, and yields mesh saliency that agrees with human perception. The algorithm is tested on many models and outperformed previous works. We also demonstrated the benefits of our algorithm in some geometry processing applications.

Keywords Visual perception; Mesh saliency; Sampling; Simplification; Mesh smoothing
Paper PDF
Motivation Principles of visual saliency
  • Principle I: local contrast. High contrast against its local surrounding indicates high saliency. Salient regions always have distinctive differences with their local neighbors.
  • Principle II: global rarity. Global rarity in the entire scene means more attention and high saliency. Many studies have shown that human visual system is sensitive to less frequent features and suppress frequently features. This is consistent with human intuition. See the following figure.




Overview of our approach.


Mesh saliency results on various models. Left: our results; right: the results of [7]. The corresponding histogram shows the distribution of saliency.



Thanks to the reviewers for their constructive comments. This work is supported by the National Natural Science Foundation of China (61070071, 61222206) and the National Basic Research Program of China (2011CB302400).

BibTex @article {Wu:Saliency2013,
    title = {Mesh saliency with global rarity},
    author = {Jinliang Wu and Xiaoyong Shen and Wei Zhu and Ligang Liu}
    journal = {Graphical Models},
    volume = {75},
    Issue = {5},
    pages = {255-264},
    year = {2013}

Back to Homepage

Copyright and disclaimer:
Copyright © Ligang Liu
The SOFTWARE provided at this page is provided "as is", without any guarantee made as to its suitability or fitness for any particular use. It may contain bugs, so use of this tool is at your own risk. We take no responsibility for any damage that may unintentionally be caused through its use.