MO-Transformer: A Transformer-Based Multi-Object Point Cloud Reconstruction Network

Erli Lyu, Zhengyan Zhang, Wei Liu, Jiaole Wang, Shuang Song, Max Q.‐h. MengIROS 2022 · DOI

Abstract

This paper proposes a new network for reconstructing multi-object point cloud. Different from previous networks which reconstruct multi-object point cloud as a whole, our network iteratively reconstructs each individual object point cloud from a frame of multi-object point cloud. To achieve this goal, we have designed MO-Transformer, a transformer-based autoregressive network. During training, MO-Transformer takes a frame of multi-object point cloud and individual object point clouds as input. During testing, MO-Transformer iteratively reconstructs individual object point clouds only based on the input multi-object point cloud. To train the proposed MO-Transformer, we design a new loss function called separate Chamfer distance (SCD). In addition, we prove that SCD is an upper bound of the traditional Chamfer distance calculated based on the entire multi-object point cloud. The reconstruction experiment verifies the efficacy of our network in multi-object point cloud reconstruction. Furthermore, the reconstruction experiment also investigates the effect of different dimensions using a series of datasets. The ablation study experiment verifies the necessity of SCD in training MO-Transformer.
BibTeX
@inproceedings{lyu2022mo,
  author = {Erli Lyu and Zhengyan Zhang and Wei Liu and Jiaole Wang and Shuang Song and Max Q.‐H. Meng},
  title = {{MO-Transformer: A Transformer-Based Multi-Object Point Cloud Reconstruction Network}},
  booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems},
  year = {2022},
  doi = {10.1109/iros47612.2022.9981837},
}

Loading related content...

Figure