mlsanityData to 14 Oct 2026

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

arXiv 2111.13386 ↗First posted 26 Nov 2021cs.CVcited by 6

Not on the map. Why?

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 %.

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

18 of 23 references.

References · 18

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
  8. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  9. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  10. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  11. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 235
  12. 2020ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functionscited by 184
6 more
  1. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  2. 2019Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaningcited by 58
  3. 2020BiDet: An Efficient Binarized Object Detectorcited by 33
  4. 2020BiPointNet: Binary Neural Network for Point Cloudscited by 30
  5. 2018Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagationcited by 29
  6. 2019Bayesian Optimized 1-Bit CNNscited by 14

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1; 2024: 1; 2025: 1.

6 papers.

  1. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 362
  2. 2022Recurrent Bilinear Optimization for Binary Neural Networkscited by 12
  3. 2022IDa-Det: An Information Discrepancy-aware Distillation for 1-bit Detectorscited by 12
  4. 2023BPT: Binary Point Cloud Transformer for Place Recognitioncited by 1
  5. 2024FBPT: A Fully Binary Point Transformercited by 1
  6. 2025BiVM: Accurate Binarized Neural Network for Efficient Video Mattingcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2023Binarizing Sparse Convolutional Networks for Efficient Point Cloud Analysis
  2. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies
  3. 2025BD-Net: Has Depth-Wise Convolution Ever Been Applied in Binary Neural Networks?
  4. 2022Binary Neural Networks as a general-propose compute paradigm for on-device computer vision
  5. 2022Exploiting Kernel Compression on BNNs
  6. 2021BCNN: Binary Complex Neural Network
  7. 2022Join the High Accuracy Club on ImageNet with A Binary Neural Network Ticket
  8. 2025PointCNN++: Performant Convolution on Native Points