Lossy Geometry Compression Of 3d Point Cloud Data Via An Adaptive Octree-Guided Network

Xuanzheng Wen, Xu Wang, Junhui Hou, Lin Ma, Yu Zhou, Jianmin Jiang

Abstract

In this paper, we propose a deep learning based framework for point cloud geometry lossy compression via hybrid representation of point cloud. First, the input raw 3D point cloud data is adaptively decomposed into non-overlapping local patches through adaptive Octree decomposition and clustering. Second, a framework of point cloud auto-encoder network with quantization layer is proposed for learning compact latent feature representation from each patch. Specifically, the proposed point cloud auto-encoder networks with different input size are trained for achieving optimal rate-distortion (RD) performance. Final, bitstream specifications of proposed compression systems with additional signaled meta-data and header information are designed to support parallel decoding and successive reconstruction. Experimental results shows that our proposed method can achieve 40.20% bitrate saving in average than the existing standard Geometry based Point Cloud Compression (G-PCC) codec.
BibTeX
@inproceedings{wen2020lossy,
  author = {Xuanzheng Wen and Xu Wang and Junhui Hou and Lin Ma and Yu Zhou and Jianmin Jiang},
  title = {{Lossy Geometry Compression Of 3d Point Cloud Data Via An Adaptive Octree-Guided Network}},
  booktitle = {ICME},
  year = {2020},
  doi = {10.1109/icme46284.2020.9102866},
}

Loading related content...

Figure