[Ari 18, 2023] The paper is accepted by Multimedia tools and applications.
[Mar 29, 2022] We submit a new paper to Multimedia tools and applications.
[Dec 8, 2021] We submit a new paper to IEEE Computer Grapics and Applications.
[Apr 18, 2021] We release the project page in github.
[Apr 16, 2021] The paper is labeled as early access by IEEE Transactions on Multimedia.
[Apr 9, 2021] The paper is accepted by IEEE Transactions on Multimedia.
[Nov 15, 2020] The paper is submitted into IEEE Transactions on Multimedia.
[Jun 15, 2020] The project is activated.

Mesh reconstruction from a 3D point cloud is an important topic in the fields of computer graphic, computer vision, and multimedia analysis. In this paper, we propose a voxel structure-based mesh reconstruction framework. It provides the intrinsic metric to improve the accuracy of local region detection. Based on the detected local regions, an initial reconstructed mesh can be obtained. With the mesh optimization in our framework, the initial reconstructed mesh is optimized into an isotropic one with the important geometric features such as external and internal edges. The experimental results indicate that our framework shows great advantages over peer ones in terms of mesh quality, geometric feature keeping, and processing speed.

[1] Lv C, Lin W, Zhao B. Voxel structure-based mesh reconstruction from a 3D point cloud[J]. IEEE Transactions on Multimedia, 2021, 24: 1815-1829.
Bib:
@article{Lvvoxel2021,
     title={Voxel Structure-based Mesh Reconstruction from a 3D Point Cloud},
     author={C. {Lv} and W. {Lin} and B. {Zhao}},
     journal={IEEE Transactions on Multimedia},
     volume={24},
     pages={1815--1829},
     year={2021},
     publisher={IEEE}
}

This research is supported by the Ministry of Education, Singapore.