Sparse Metric-based Mesh Saliency

Shanfeng Hu, Xiaohui Liang, Hubert P. H. Shum, Frederick W. B. Li and Nauman Aslam
Neurocomputing, 2020

Impact Factor: 5.779# Citation: 3##

Sparse Metric-based Mesh Saliency
# Impact factors from the Journal Citation Reports 2021
## Citation counts from Google Scholar as of 2022

Abstract

In this paper, we propose an accurate and robust approach to salient region detection for 3D polygonal surface meshes. The salient regions of a mesh are those that geometrically stand out from their contexts and therefore are semantically important for geometry processing and shape analysis. However, a suitable definition of region contexts for saliency detection remains elusive in the field, and the previous methods fail to produce saliency maps that agree well with human annotations. We address these issues by computing saliency in a global manner and enforcing sparsity for more accurate saliency detection. Specifically, we represent the geometry of a mesh using a metric that globally en- codes the shape distances between every pair of local regions. We then propose a sparsity-enforcing rarity optimization problem, solving which allows us to obtain a compact set of salient regions globally distinct from each other. We build a perceptually motivated 3D eye fixation dataset and use a large-scale Schelling saliency dataset for extensive benchmarking of saliency detection methods. The results show that our computed saliency maps are closer to the ground-truth. To showcase the usefulness of our saliency maps for geometry processing, we apply them to feature point localization and achieve higher accuracy compared to established feature detectors.

Downloads

YouTube

Citations

BibTeX

@article{hu20sparse,
 author={Hu, Shanfeng and Liang, Xiaohui and Shum, Hubert P. H. and Li, Frederick W. B. and Aslam, Nauman},
 journal={Neurocomputing},
 title={Sparse Metric-based Mesh Saliency},
 year={2020},
 volume={400},
 pages={11--23},
 numpages={13},
 doi={10.1016/j.neucom.2020.02.106},
 issn={0925-2312},
 publisher={Elsevier},
}

RIS

TY  - JOUR
AU  - Hu, Shanfeng
AU  - Liang, Xiaohui
AU  - Shum, Hubert P. H.
AU  - Li, Frederick W. B.
AU  - Aslam, Nauman
T2  - Neurocomputing
TI  - Sparse Metric-based Mesh Saliency
PY  - 2020
VL  - 400
SP  - 11
EP  - 23
DO  - 10.1016/j.neucom.2020.02.106
SN  - 0925-2312
PB  - Elsevier
ER  - 

Plain Text

Shanfeng Hu, Xiaohui Liang, Hubert P. H. Shum, Frederick W. B. Li and Nauman Aslam, "Sparse Metric-based Mesh Saliency," Neurocomputing, vol. 400, pp. 11-23, Elsevier, 2020.

Similar Research

Shanfeng Hu, Hubert P. H. Shum, Nauman Aslam, Frederick W. B. Li and Xiaohui Liang, "A Unified Deep Metric Representation for Mesh Saliency Detection and Non-rigid Shape Matching", IEEE Transactions on Multimedia (TMM), 2020

 

 

Last updated on 19 January 2023
RSS Feed