NVlabs / Splatnet
Licence: other
SPLATNet: Sparse Lattice Networks for Point Cloud Processing (CVPR2018)
Stars: ✭ 259
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Splatnet
Probreg
Python package for point cloud registration using probabilistic model (Coherent Point Drift, GMMReg, SVR, GMMTree, FilterReg, Bayesian CPD)
Stars: ✭ 306 (+18.15%)
Mutual labels: 3d, point-cloud
3d Machine Learning
A resource repository for 3D machine learning
Stars: ✭ 7,405 (+2759.07%)
Mutual labels: 3d, point-cloud
Atlasnet
This repository contains the source codes for the paper "AtlasNet: A Papier-Mâché Approach to Learning 3D Surface Generation ". The network is able to synthesize a mesh (point cloud + connectivity) from a low-resolution point cloud, or from an image.
Stars: ✭ 450 (+73.75%)
Mutual labels: 3d, cvpr2018
3dmatch Toolbox
3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.
Stars: ✭ 571 (+120.46%)
Mutual labels: 3d, point-cloud
So Net
SO-Net: Self-Organizing Network for Point Cloud Analysis, CVPR2018
Stars: ✭ 297 (+14.67%)
Mutual labels: 3d, point-cloud
Cilantro
A lean C++ library for working with point cloud data
Stars: ✭ 577 (+122.78%)
Mutual labels: 3d, point-cloud
Dbnet
DBNet: A Large-Scale Dataset for Driving Behavior Learning, CVPR 2018
Stars: ✭ 172 (-33.59%)
Mutual labels: point-cloud, cvpr2018
Votenet
Deep Hough Voting for 3D Object Detection in Point Clouds
Stars: ✭ 1,183 (+356.76%)
Mutual labels: 3d, point-cloud
Frustum Pointnets
Frustum PointNets for 3D Object Detection from RGB-D Data
Stars: ✭ 1,154 (+345.56%)
Mutual labels: 3d, point-cloud
3d Bounding Boxes From Monocular Images
A two stage multi-modal loss model along with rigid body transformations to regress 3D bounding boxes
Stars: ✭ 24 (-90.73%)
Mutual labels: 3d, point-cloud
Meshlab
The open source mesh processing system
Stars: ✭ 2,619 (+911.2%)
Mutual labels: 3d, point-cloud
Pangolin
Python binding of 3D visualization library Pangolin
Stars: ✭ 157 (-39.38%)
Mutual labels: 3d, point-cloud
3d Bat
3D Bounding Box Annotation Tool (3D-BAT) Point cloud and Image Labeling
Stars: ✭ 179 (-30.89%)
Mutual labels: 3d, point-cloud
pointnet2 semantic
A pointnet++ fork, with focus on semantic segmentation of differents datasets
Stars: ✭ 69 (-73.36%)
Mutual labels: point-cloud
Iterative-Closest-Point
Implementation of the iterative closest point algorithm. A point cloud is transformed such that it best matches a reference point cloud.
Stars: ✭ 101 (-61%)
Mutual labels: point-cloud
pointnet2-pytorch
A clean PointNet++ segmentation model implementation. Support batch of samples with different number of points.
Stars: ✭ 45 (-82.63%)
Mutual labels: point-cloud
3D-Engine-OpenGL-4
3D Graphics Engine For Games | C++ OpenGL 4.1
Stars: ✭ 19 (-92.66%)
Mutual labels: 3d
SPLATNet: Sparse Lattice Networks for Point Cloud Processing (CVPR2018)
License
Copyright (C) 2018 NVIDIA Corporation. All rights reserved. Licensed under the CC BY-NC-SA 4.0 license (https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
Paper
@inproceedings{su18splatnet,
author={Su, Hang and Jampani, Varun and Sun, Deqing and Maji, Subhransu and Kalogerakis, Evangelos and Yang, Ming-Hsuan and Kautz, Jan},
title = {{SPLATN}et: Sparse Lattice Networks for Point Cloud Processing},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages = {2530--2539},
year = {2018}
}
Usage
-
Install Caffe and bilateralNN
Note that our code uses Python3.
- Please follow the instructions on the bilateralNN repo.
- A step-by-step installation guide for Ubuntu 16.04 is provided in INSTALL.md.
- Alternatively, you can install nvidia-docker and use this docker image:
docker pull suhangpro/caffe:bpcn
You can also build this image with the Dockerfile. - The docker image provided above uses CUDA 8, which is no longer supported if you have Volta GPUs (e.g. Titan V), Turing GPUs (e.g. RTX 2080), or newer ones. Adapting the Dockerfile to more recent GPUs should be straightforward—check out the example supporting up to Turing, courtesy of @zyzwhdx.
-
Include the project to your python path so imports can be found, e.g.
export PYTHONPATH=<PATH_TO_PROJECT_ROOT>:$PYTHONPATH
-
Download and prepare data files under folder
data/
See instructions in data/README.md.
-
Usage examples
- 3D facade segmentation
- test pre-trained model
cd exp/facade3d ./dl_model_facade3d.sh # download pre-trained model SKIP_TRAIN=1 ./train_test.sh
Prediction is output atpred_test.ply
, with evaluation results intest.log
. - or, train and evaluate
cd exp/facade3d ./train_test.sh
- test pre-trained model
- ShapeNet Part segmentation
- test pre-trained model
cd exp/shapenet3d ./dl_model_shapenet3d.sh # download pre-trained model ./test_only.sh
Predictions are underpred/
, with evaluation results intest.log
. - or, train and evaluate
cd exp/shapenet3d ./train_test.sh
- test pre-trained model
- 3D facade segmentation
References
We make extensive use of bilateralNN, which is proposed in these publications:
- V. Jampani, M. Kiefel and P. V. Gehler. Learning Sparse High-Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks. CVPR, 2016.
- M.Kiefel, V. Jampani and P. V. Gehler. Permutohedral Lattice CNNs. ICLR Workshops, 2015.
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].