/CCPNet

3D Semantic Scene Completion

                             IIAU (2019) 3D Semantic Scene Completion

Introduction

This file contains our Semantic Scene Completion models appeared in ICCV2019.

  1. CCPNet Title: Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion
    Authors: Pingping Zhang, Wei Liu, Yinjie Lei, Huchuan Lu*and Xiaoyun Yang
    Paper Links: Arxiv: https://arxiv.org/pdf/1908.00382.pdf
    Baidu Pan：https://pan.baidu.com/s/1DdrEym-xEE5ugt_dD2JZjA
    How to use

Prerequisites:
Caffe-3D
Follow the official websites of the Caffe framework and install the whole toolbox (necessary Matlab wrappers)

  1. Training
    The training code is coming soon. For saving memory, we use the BN method implemented by Alex Kendall etal http://mi.eng.cam.ac.uk/projects/segnet/. The training is followed as examples in Caffe. We use the ImageData layer to load training image pairs. The only need is changing the path of data files.
  2. Testing The testing code is coming soon.

Results

The completion results can be download via baidu yun.

Citation

Please cite the following papers if our models help your research:
@article{zhang2019cascaded,
title={Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion},
author={Zhang, Pingping and Liu, Wei and Lei, Yinjie and Lu, Huchuan and Yang, Xiaoyun},
journal={arXiv preprint arXiv:1908.00382},
year={2019}
} @InProceedings{Zhang_2019_ICCV,
author = {Zhang, Pingping and Liu, Wei and Lei, Yinjie and Lu, Huchuan and Yang, Xiaoyun},
title = {Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2019}
}

Question and connection

If any question, please connect jssxzhpp@gmail.com; jssxzhpp@mail.dlut.edu.cn