POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing

2021/11/26 by Sheng Xu, Xu, Sheng, Yanjing Li +7 · 1 citation
Computer Science · Engineering · #3D Shape Modeling and Analysis #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition

paper · pdf · doi:10.48550/arxiv.2111.13386

openalex publication_date 2021/11/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Real-time point cloud processing is fundamental for lots of computer vision tasks, while still challenged by the computational problem on resource-limited edge devices. To address this issue, we implement XNOR-Net-based binary neural networks (BNNs) for an efficient point cloud processing, but its performance is severely suffered due to two main drawbacks, Gaussian-distributed weights and non-learnable scale factor. In this paper, we introduce point-wise operations based on Expectation-Maximization (POEM) into BNNs for efficient point cloud processing. The EM algorithm can efficiently constrain weights for a robust bi-modal distribution. We lead a well-designed reconstruction loss to calculate learnable scale factors to enhance the representation capacity of 1-bit fully-connected (Bi-FC) layers. Extensive experiments demonstrate that our POEM surpasses existing the state-of-the-art binary point cloud networks by a significant margin, up to 6.7 %.

Citations

• The expectation-maximization algorithm
• ShapeNet: An Information-Rich 3D Model Repository
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Dynamic Graph CNN for Learning on Point Clouds

Cited by

• BiVM: Accurate Binarized Neural Network for Efficient Video Matting

Related

• BiPointNet: Binary Neural Network for Point Clouds
• Binary Neural Networks as a general-propose compute paradigm for on-device computer vision
• Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket
• RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs
• FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going Beyond