DeepAI AI Chat
Log In Sign Up

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

by   Radu Alexandru Rosu, et al.

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.


page 8

page 10

page 11


LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices

Deep convolutional neural networks (CNNs) have shown outstanding perform...

NPTC-net: Narrow-Band Parallel Transport Convolutional Neural Network on Point Clouds

Convolution plays a crucial role in various applications in signal and i...

Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients

Deep neural networks for 3D point cloud classification, such as PointNet...

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

We present a network architecture for processing point clouds that direc...

3DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCN

Deep learning on point clouds has made a lot of progress recently. Many ...

Learning Hybrid Representations for Automatic 3D Vessel Centerline Extraction

Automatic blood vessel extraction from 3D medical images is crucial for ...

Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation

3D point clouds can flexibly represent continuous surfaces and can be us...