All Projects → yanx27 → Gacnet

yanx27 / Gacnet

Pytorch implementation of 'Graph Attention Convolution for Point Cloud Segmentation'

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Gacnet

point-cloud-segmentation
TF2 implementation of PointNet for segmenting point clouds
Stars: ✭ 33 (-67.96%)
Mutual labels:  point-cloud, segmentation
pointnet2-pytorch
A clean PointNet++ segmentation model implementation. Support batch of samples with different number of points.
Stars: ✭ 45 (-56.31%)
Mutual labels:  point-cloud, segmentation
pyRANSAC-3D
A python tool for fitting primitives 3D shapes in point clouds using RANSAC algorithm
Stars: ✭ 253 (+145.63%)
Mutual labels:  point-cloud, segmentation
Pointnet2
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
Stars: ✭ 2,197 (+2033.01%)
Mutual labels:  point-cloud, segmentation
Depth clustering
🚕 Fast and robust clustering of point clouds generated with a Velodyne sensor.
Stars: ✭ 657 (+537.86%)
Mutual labels:  point-cloud, segmentation
3d Pointcloud
Papers and Datasets about Point Cloud.
Stars: ✭ 179 (+73.79%)
Mutual labels:  point-cloud, segmentation
torch-points3d
Pytorch framework for doing deep learning on point clouds.
Stars: ✭ 1,823 (+1669.9%)
Mutual labels:  point-cloud, segmentation
Pointnet Keras
Keras implementation for Pointnet
Stars: ✭ 110 (+6.8%)
Mutual labels:  point-cloud, segmentation
Cilantro
A lean C++ library for working with point cloud data
Stars: ✭ 577 (+460.19%)
Mutual labels:  point-cloud, segmentation
Superpoint graph
Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs
Stars: ✭ 533 (+417.48%)
Mutual labels:  point-cloud, segmentation
Pointasnl
PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling (CVPR 2020)
Stars: ✭ 159 (+54.37%)
Mutual labels:  point-cloud, segmentation
Torch Points3d
Pytorch framework for doing deep learning on point clouds.
Stars: ✭ 1,135 (+1001.94%)
Mutual labels:  point-cloud, segmentation
Dgcnn.pytorch
A PyTorch implementation of Dynamic Graph CNN for Learning on Point Clouds (DGCNN)
Stars: ✭ 153 (+48.54%)
Mutual labels:  point-cloud, segmentation
3dgnn pytorch
3D Graph Neural Networks for RGBD Semantic Segmentation
Stars: ✭ 187 (+81.55%)
Mutual labels:  point-cloud, segmentation
Grid Gcn
Grid-GCN for Fast and Scalable Point Cloud Learning
Stars: ✭ 143 (+38.83%)
Mutual labels:  point-cloud, segmentation
Point2Sequence
Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network
Stars: ✭ 34 (-66.99%)
Mutual labels:  point-cloud, segmentation
Pointnet
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Stars: ✭ 3,517 (+3314.56%)
Mutual labels:  point-cloud, segmentation
Pointcnn
PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)
Stars: ✭ 1,120 (+987.38%)
Mutual labels:  point-cloud, segmentation
Pointclouddatasets
3D point cloud datasets in HDF5 format, containing uniformly sampled 2048 points per shape.
Stars: ✭ 80 (-22.33%)
Mutual labels:  point-cloud, segmentation
Pixeltcn
Tensorflow Implementation of Pixel Transposed Convolutional Networks (PixelTCN and PixelTCL)
Stars: ✭ 91 (-11.65%)
Mutual labels:  segmentation

Graph Attention Convolution for Point Cloud Segmentation

This is personal pytorch implmentation of GACNet on S3DIS dataset, but not official version.

Download Data

Run download_data.sh and save dataset in ./indoor3d_sem_seg_hdf5_data/

Train Model

Run python train_semseg.py

Announcement

It is only a personal implmentation, and the experimental results do not represent the model in paper. There are still many hyper parameters that need to be adjusted when the author publishes the source code.

Environments

Ubuntu 16.04
Python 3.6.5
Pytorch 0.4.1

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].