Weighted Voxel

Weighted Voxel: a novel voxel representation for 3D reconstruction

Haozhe Xie, Hongxun Yao, Xiaoshuai Sun, Shangchen Zhou, Xiaojun Tong

Overview of Weighted Voxel

Abstract

3D reconstruction has been attracting increasing attention in the past few years. With the surge of deep neural networks, the performance of 3D reconstruction has been improved significantly. However, the voxel reconstructed by extant approaches usually contains lots of noise and leads to heavy computation. In this paper, we define a new voxel representation, named Weighted Voxel. It provides more abundant information, facilitating the subsequent learning and generalization steps. Unlike regular voxel which consists of zero-one, the proposed Weighted Voxel makes full use of the structure information of voxels. Experimental results demonstrate that Weighted Voxel not only performs better in reconstruction but also takes less time in training.

Spotlight Video

If you cannot access YouTube, please watch the video here.

Paper

  • Haozhe Xie, Hongxun Yao, Xiaoshuai Sun, Shangchen Zhou, Xiaojun Tong. Weighted Voxel: a novel voxel representation for 3D reconstruction. International Conference on Internet Multimedia Computing and Service (ICIMCS), 2018.
    [BibTeX] [PDF]
    @inproceedings{xie2018weighted,
      title={Weighted Voxel: a novel voxel representation for 3D reconstruction},
      author={Xie, Haozhe and Yao, Hongxun and Sun, Xiaoshuai and Zhou, Shangchen and Tong, Xiaojun},
      booktitle={International Conference on Internet Multimedia Computing and Service (ICIMCS)},
      year={2018},
      organization={acm}
    }

Source Code

We provide source code for the project on GitHub.

Datasets

We used ShapeNet models to generate rendered images and voxelized models which are available below.

License

This project is open sourced under MIT license.

Contact Us
  • SenseTime Research, Shenzhen Bay Eco-Technology Park
  • cshzxie [at] gmail [dot] com