Registration Loss Learning for Deep Probabilistic Point Set Registration

Related tags

Deep Learning RLLReg
Overview

RLLReg

This repository contains a Pytorch implementation of the point set registration method RLLReg. Details about the method can be found in the 3DV 2020 paper "Registration Loss Learning for Deep Probabilistic Point Set Registration".

ArXiv: [paper]

If you find the code useful, please cite using

@InProceedings{Lawin_2020_3DV,
    author = {Felix J\"aremo Lawin and Per-Erik Forss\'en},
    title = {Registration Loss Learning for Deep Probabilistic Point Set Registration},
    booktitle = {{IEEE/CVF} International Virtual Conference on 3D Vision ({3DV})},
    month = {November},
    year = {2020}} 

Installation

  • Clone the repository: git clone https://github.com/felja633/RLLReg.git
  • Create a conda environment and install the following dependencies:
conda create -n rllreg python=3.7
conda activate rllreg
conda install -y numpy pathlib mkl-include pyyaml
conda install -y pytorch==1.6.0 torchvision==0.7.0 cudatoolkit=10.2 -c pytorch
conda install -y -c conda-forge cudatoolkit-dev
pip install easydict visdom
pip install git+https://github.com/jonbarron/robust_loss_pytorch
conda install -y -c open3d-admin open3d
git clone https://github.com/NVIDIA/MinkowskiEngine.git
cd MinkowskiEngine
python setup.py install --cuda_home=/path/to/conda/rllreg 
pip install torch-scatter==latest+cu102 -f https://pytorch-geometric.com/whl/torch-1.6.0.html
pip install torch-sparse==latest+cu102 -f https://pytorch-geometric.com/whl/torch-1.6.0.html
pip install torch-cluster==latest+cu102 -f https://pytorch-geometric.com/whl/torch-1.6.0.html
pip install torch-spline-conv==latest+cu102 -f https://pytorch-geometric.com/whl/torch-1.6.0.html
pip install torch-geometric

Datasets

Kitti

Download and unpack Velodyne scans from http://www.cvlibs.net/download.php?file=data_odometry_velodyne.zip

3DMatch

Download RGB-D scenes from http://3dmatch.cs.princeton.edu/ using http://vision.princeton.edu/projects/2016/3DMatch/downloads/rgbd-datasets/download.sh and unpack the file. Download train.txt and test.txt. These contain the official train/test splits which can be found in the file https://vision.princeton.edu/projects/2016/3DMatch/downloads/rgbd-datasets/split.txt. Place these text files in the 3DMatch dataset folder.

Configuration

Set up your local environment by setting the correct paths for your system in config.py. Here you should set the paths to the datasets and pre-trained models.

Models

The following pre-trained models are available for download:

Name Training set Weights
RLLReg_threedmatch.pth 3DMatch download
RLLReg_threedmatch_multi.pth 3DMatch download
RLLReg_kitti.pth Kitti download
RLLReg_kitti_multi.pth Kitti download

For the version trained with contrastive loss, use the following models from https://github.com/chrischoy/FCGF

Name Training set Weights
2019-08-16_19-21-47.pth 3DMatch download
KITTI-v0.3-ResUNetBN2C-conv1-5-nout16.pth Kitti download

To further enable comparisons to DGR, download the weights for 3DMatch and Kitti.

Place all pre-trained weights in the same folder and set pretrained_networks to the path of that folder in config.py.

Running evaluations

Scripts for evaluation are available at experiments/. For an evaluation of pairwise registration as described in the paper run:

python experiments/evaluation_kitti.py

Training

Scripts for training are available at experiments/. If you want to train RLLReg for pairwise registration run:

python experiments/train_rll_kitti.py

Additional implementations

This repository also includes a pytorch version of Density Adaptive Point Set Registration (DARE) and Joint Registration of Multiple Point Clouds (JRMPC). Further, models/feature_reg_model_fcgf_fppsr.py and models/feature_reg_model_fpfh_fppsr.py contain pytorch implementations of FPPSR using FCGF and FPFH features respectively.

Under external/DeepGLobalRegistration the official implementation of DGR is located. The code is copied from the original repository but it is modified to use relative paths.

Contact

Felix Järemo Lawin

email: [email protected]

Acknowledgements

Special thanks go to Shivangi Srivastava who helped with initial implementations of the work!

Issues
  • Some question about evaluation_threedmatch.py

    Some question about evaluation_threedmatch.py

    I download RGB-D scenes from 3dmatch and pre-trained models. After set pretrained_networks and 3dmatch dataset to the path of that folder in config.py, I run the following script: python evaluation_threedmatch.py => loading checkpoint '/home/s206/disk/pycharmproject/RLLReg-master/data/models/ResUNetBN2C-feat32-3dmatch-v0.05.pth' => Setting voxel size to 0.05 => loading finished generate samples... evaluate batch 0 ... RLLReg resample time: 449.2 ms extract time: 644.6 ms Traceback (most recent call last): File "evaluation_threedmatch.py", line 140, in max_err_R=4.0, max_err_t=0.3, success_R=4, success_t=0.1, save_errors=True, plot=False) File "/home/s206/disk/pycharmproject/RLLReg-master/evaluation/evaluate.py", line 36, in benchmark errors[m.params.name].append(evaluate_registration(m, batch, vis, save=save)) File "/home/s206/disk/pycharmproject/RLLReg-master/evaluation/evaluate.py", line 10, in evaluate_registration out = method(data) File "/home/s206/anaconda3/envs/rllreg/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/s206/disk/pycharmproject/RLLReg-master/models/rll_model_fcgf.py", line 164, in forward assert f.shape[0] == inds_list[ind_cnt].shape[0] AssertionError It seems the code doesn't run rightly. My torch version is 1.7 and minkowskiEngine version is 0.4. Can you help me?

    opened by Yellowshuohahaha 4
Owner
Felix Järemo Lawin
Felix Järemo Lawin
Implement of "Training deep neural networks via direct loss minimization" in PyTorch for 0-1 loss

This is the implementation of "Training deep neural networks via direct loss minimization" published at ICML 2016 in PyTorch. The implementation targe

Cuong Nguyen 1 Jan 18, 2022
[PyTorch] Official implementation of CVPR2021 paper "PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency". https://arxiv.org/abs/2103.05465

PointDSC repository PyTorch implementation of PointDSC for CVPR'2021 paper "PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency",

null 126 Jun 29, 2022
Automatically download the cwru data set, and then divide it into training data set and test data set

Automatically download the cwru data set, and then divide it into training data set and test data set.自动下载cwru数据集,然后分训练数据集和测试数据集

null 6 Jun 27, 2022
Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation)

Recall Loss for Semantic Segmentation (This repo implements the paper: Recall Loss for Semantic Segmentation) Download Synthia dataset The model uses

null 29 Jun 2, 2022
An implementation for the loss function proposed in Decoupled Contrastive Loss paper.

Decoupled-Contrastive-Learning This repository is an implementation for the loss function proposed in Decoupled Contrastive Loss paper. Requirements P

Ramin Nakhli 55 Jun 5, 2022
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)

Bayesian Methods for Hackers Using Python and PyMC The Bayesian method is the natural approach to inference, yet it is hidden from readers behind chap

Cameron Davidson-Pilon 24.6k Jul 1, 2022
MVP Benchmark for Multi-View Partial Point Cloud Completion and Registration

MVP Benchmark: Multi-View Partial Point Clouds for Completion and Registration [NEWS] 2021-07-12 [NEW ?? ] The submission on Codalab starts! 2021-07-1

PL 87 Jun 26, 2022
Compute descriptors for 3D point cloud registration using a multi scale sparse voxel architecture

MS-SVConv : 3D Point Cloud Registration with Multi-Scale Architecture and Self-supervised Fine-tuning Compute features for 3D point cloud registration

null 42 Jun 15, 2022
You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors

You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors In this paper, we propose a novel local descriptor-based fra

Haiping Wang 56 Apr 21, 2022
Point Cloud Registration using Representative Overlapping Points.

Point Cloud Registration using Representative Overlapping Points (ROPNet) Abstract 3D point cloud registration is a fundamental task in robotics and c

ZhuLifa 29 Jun 13, 2022
Cascading Feature Extraction for Fast Point Cloud Registration (BMVC 2021)

Cascading Feature Extraction for Fast Point Cloud Registration This repository contains the source code for the paper [Arxive link comming soon]. Meth

null 7 May 26, 2022
PyTorch implementation of NeurIPS 2021 paper: "CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration"

PyTorch implementation of NeurIPS 2021 paper: "CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration"

null 65 Jun 6, 2022
Point Cloud Registration Network

PCRNet: Point Cloud Registration Network using PointNet Encoding Source Code Author: Vinit Sarode and Xueqian Li Paper | Website | Video | Pytorch Imp

ViNiT SaRoDe 51 Jun 8, 2022
GeoTransformer - Geometric Transformer for Fast and Robust Point Cloud Registration

Geometric Transformer for Fast and Robust Point Cloud Registration PyTorch imple

Zheng Qin 138 Jun 23, 2022
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds (CVPR 2022, Oral)

Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds (CVPR 2022, Oral) This is the official implementat

Yifan Zhang 149 Jul 1, 2022
DeepProbLog is an extension of ProbLog that integrates Probabilistic Logic Programming with deep learning by introducing the neural predicate.

DeepProbLog DeepProbLog is an extension of ProbLog that integrates Probabilistic Logic Programming with deep learning by introducing the neural predic

KU Leuven Machine Learning Research Group 73 Jun 29, 2022
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021)

Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021) An efficient PyTorch library for Point Cloud Completion.

Microsoft 108 Jun 27, 2022
Implementation of the "PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences" paper.

PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences Introduction Point cloud sequences are irregular and unordered in the spatial dimen

Hehe Fan 59 Jun 21, 2022
Code for "PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds", CVPR 2021

PV-RAFT This repository contains the PyTorch implementation for paper "PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clou

Yi Wei 38 May 23, 2022