mlsanityData to 14 Oct 2026

LatticeNet: Fast Spatio-Temporal Point Cloud Segmentation Using Permutohedral Lattices

arXiv 2108.03917 ↗First posted 9 Aug 2021cs.CV cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. Applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of structured data. Here, we propose LatticeNet, a novel approach for 3D semantic segmentation, which takes raw point clouds as input. A PointNet describes the local geometry which we embed into a sparse permutohedral lattice. The lattice allows for fast convolutions while keeping a low memory footprint. Further, we introduce DeformSlice, a novel learned data-dependent interpolation for projecting lattice features back onto the point cloud. We present results of 3D segmentation on multiple datasets where our method achieves state-of-the-art performance. We also extend and evaluate our network for instance and dynamic object segmentation.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 42 of its 55 references that are in the map. First posted on arXiv 9 Aug 2021.

Builds on

42 of 55 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Densely Connected Convolutional Networkscited by 6,720
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  9. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  10. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  11. 2018Group Normalizationcited by 1,524
  12. 2017Deep Setscited by 1,421
30 more
  1. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  2. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  3. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  4. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  5. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  6. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  7. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  8. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 465
  9. 2014cuDNN: Efficient Primitives for Deep Learningcited by 245
  10. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  11. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  12. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  13. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 169
  14. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  15. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  16. 2019Learning Object Bounding Boxes for 3D Instance Segmentation on Point Cloudscited by 156
  17. 2018GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudcited by 146
  18. 2017Semantic Instance Segmentation with a Discriminative Loss Functioncited by 118
  19. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  20. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 109
  21. 2019Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidthcited by 89
  22. 2019Associatively Segmenting Instances and Semantics in Point Cloudscited by 86
  23. 2019JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fieldscited by 62
  24. 2018TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshescited by 45
  25. 2018Fully-Convolutional Point Networks for Large-Scale Point Cloudscited by 44
  26. 2019LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Latticescited by 38
  27. 2018Real-time Progressive 3D Semantic Segmentation for Indoor Scenecited by 18
  28. 2018Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functionscited by 7
  29. 2019Efficient 3D Reconstruction and Streaming for Group-Scale Multi-Client Live Telepresencecited by 2
  30. 2019Bonn Activity Maps: Dataset Descriptioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 1; 2025: 1; 2026: 1.

11 papers.

  1. 2022LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Cloudscited by 33
  2. 2022Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradientscited by 17
  3. 20224DenoiseNet: Adverse Weather Denoising from Adjacent Point Cloudscited by 14
  4. 2022Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Latticecited by 9
  5. 2023Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentationcited by 5
  6. 2023Using t-distributed stochastic neighbor embedding for visualization and segmentation of 3D point clouds of plantscited by 1
  7. 2023Multi-Echo Denoising in Adverse Weathercited by 1
  8. 2023Efficient Real-time Smoke Filtration with 3D LiDAR for Search and Rescue with Autonomous Heterogeneous Robotic Systemscited by 0
  9. 2024Lightweight single-image super-resolution network based on dual pathscited by 0
  10. 2025Enhancing Wide-Angle Image Using Narrow-Angle View of the Same Scenecited by 0
  11. 2026Denoising-Aware Temporal Point Cloud Completion for 3D Crop Architecture Recovery and Phenotypic Trait Extractioncited by 0