Point Cloud Segmentation
94 papers with code • 1 benchmarks • 2 datasets
3D point cloud segmentation is the process of classifying point clouds into multiple homogeneous regions, the points in the same region will have the same properties. The segmentation is challenging because of high redundancy, uneven sampling density, and lack explicit structure of point cloud data. This problem has many applications in robotics such as intelligent vehicles, autonomous mapping and navigation.
Benchmarks
These leaderboards are used to track progress in Point Cloud Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Libraries
Use these libraries to find Point Cloud Segmentation models and implementations
PointCloud-C
WaterScenes
Most implemented papers
SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation
chenfengxu714/SqueezeSegV3
•
•
ECCV 2020
Using standard convolutions to process such LiDAR images is problematic, as convolution filters pick up local features that are only active in specific regions in the image.
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud
mutianxu/GDANet
•
•
GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components.
Masked Autoencoders for Point Cloud Self-supervised Learning
Then, a standard Transformer based autoencoder, with an asymmetric design and a shifting mask tokens operation, learns high-level latent features from unmasked point patches, aiming to reconstruct the masked point patches.
OctFormer: Octree-based Transformers for 3D Point Clouds
To combat this issue, several works divide point clouds into non-overlapping windows and constrain attentions in each local window.
Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion
yanx27/JS3C-Net
•
•
In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input.
Self-Supervised Learning of Lidar Segmentation for Autonomous Indoor Navigation
utiasasrl/crystal_ball_nav
•
•
We provide insights into our network predictions and show that our approach can also improve the performances of common localization techniques.
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point positions through ScoreNet.
AGCN: Adversarial Graph Convolutional Network for 3D Point Cloud Segmentation
edshkim98/GAGCN
•
•
British Machine Vision Conference (BMVC) 2021
To overcome these problems, we propose a) a graph convolutional network (GCN) in an adversarial learning scheme where a discriminator network provides a segmentation network with informative information to improve segmentation accuracy and b) a graph convolution, GeoEdgeConv, as a means of local feature aggregation to improve segmentation accuracy and space and time complexities.
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
lulutang0608/Point-BERT
•
•
CVPR 2022
Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers.
CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation
saltoricristiano/cosmix-uda
•
•
We propose a new approach of sample mixing for point cloud UDA, namely Compositional Semantic Mix (CoSMix), the first UDA approach for point cloud segmentation based on sample mixing.
