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

arXiv: https://arxiv.org/abs/2111.13386 · HTML: https://mlsanity.com/paper/2111.13386/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 23 references that are in the map.
- First posted on arXiv 26 Nov 2021.

## Builds on (most cited first, 18 of 18)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [BinaryConnect: Training Deep Neural Networks with binary weights during propagations](https://mlsanity.com/paper/1511.00363/) (2015)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm](https://mlsanity.com/paper/1808.00278/) (2018)
- [ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions](https://mlsanity.com/paper/2003.03488/) (2020)
- [Grid-GCN for Fast and Scalable Point Cloud Learning](https://mlsanity.com/paper/1912.02984/) (2019)
- [Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning](https://mlsanity.com/paper/1904.07615/) (2019)
- [BiDet: An Efficient Binarized Object Detector](https://mlsanity.com/paper/2003.03961/) (2020)
- [BiPointNet: Binary Neural Network for Point Clouds](https://mlsanity.com/paper/2010.05501/) (2020)
- [Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation](https://mlsanity.com/paper/1811.12755/) (2018)
- [Bayesian Optimized 1-Bit CNNs](https://mlsanity.com/paper/1908.06314/) (2019)

## Built on by (most cited first, 6 of 6)

- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Recurrent Bilinear Optimization for Binary Neural Networks](https://mlsanity.com/paper/2209.01542/) (2022)
- [IDa-Det: An Information Discrepancy-aware Distillation for 1-bit Detectors](https://mlsanity.com/paper/2210.03477/) (2022)
- [BPT: Binary Point Cloud Transformer for Place Recognition](https://mlsanity.com/paper/2303.01166/) (2023)
- [FBPT: A Fully Binary Point Transformer](https://mlsanity.com/paper/2403.09998/) (2024)
- [BiVM: Accurate Binarized Neural Network for Efficient Video Matting](https://mlsanity.com/paper/2507.04456/) (2025)

## Abstract (arXiv)

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 %.