Point Cloud Processing via Recurrent Set Encoding


  • Pengxiang Wu Rutgers University
  • Chao Chen Stony Brook University
  • Jingru Yi Rutgers University
  • Dimitris Metaxas Rutgers University




We present a new permutation-invariant network for 3D point cloud processing. Our network is composed of a recurrent set encoder and a convolutional feature aggregator. Given an unordered point set, the encoder firstly partitions its ambient space into parallel beams. Points within each beam are then modeled as a sequence and encoded into subregional geometric features by a shared recurrent neural network (RNN). The spatial layout of the beams is regular, and this allows the beam features to be further fed into an efficient 2D convolutional neural network (CNN) for hierarchical feature aggregation. Our network is effective at spatial feature learning, and competes favorably with the state-of-the-arts (SOTAs) on a number of benchmarks. Meanwhile, it is significantly more efficient compared to the SOTAs.




How to Cite

Wu, P., Chen, C., Yi, J., & Metaxas, D. (2019). Point Cloud Processing via Recurrent Set Encoding. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 5441-5449. https://doi.org/10.1609/aaai.v33i01.33015441



AAAI Technical Track: Machine Learning