Deep learning image registration library for PyTorch

Last update: Dec 16, 2022

Related tags

Overview

TorchIR: Pytorch Image Registration

TorchIR is a image registration library for deep learning image registration (DLIR). I have integrated several ideas for image registration.

The current version lacks a document, but I have included quite a descriptive tutorial using MNIST data as an example. The example experiments are light-weight and should run on any CPU, although running it on a GPU will increase the speed. The notebook contains a tutorial using MNIST data as an example. Although the code runs faster on a GPU, this tutorial is small enough to run on CPU.

For the tutorial I rely on PyTorch Lightning, which can be installed via:

pip install pytorch-lightning

The pytorch-lightning trainer modules automatically create tensorboard log files. I store them in the ./output/lightning_logs directory. Simply inspect them using:

tensorboard --logdir=./output/lightning_logs

If you use this code for your publications, don't forget to cite my work ;)

[1] Bob D. de Vos, Floris F. Berendsen, Max A. Viergever, Marius Staring and Ivana Išgum, "End-to-end unsupervised deformable image registration with a convolutional neural network," in Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, Cham, 2017. p. 204-212, doi: 10.1007/978-3-319-67558-9_24 https://link.springer.com/chapter/10.1007%2F978-3-319-67558-9_24

[2] Bob D. de Vos, Floris F. Berendsen, Max A. Viergever, Hessam Sokooti, Marius Staring and Ivana Išgum "A deep learning framework for unsupervised affine and deformable image registration," Medical image analysis, vol. 52, pp. 128-143, Feb. 2019, doi: 10.1016/j.media.2018.11.010 https://www.sciencedirect.com/science/article/pii/S1361841518300495

Please note that the code is still under heavy development and I'd really love your input.

You might also like...

Python implementation of Wu et al (2018)'s registration fusion

reg-fusion Projection of a central sulcus probability map using the RF-ANTs approach (right hemisphere shown). This is a Python implementation of Wu e

26 Nov 12, 2021

UnsupervisedR&R: Unsupervised Pointcloud Registration via Differentiable Rendering

UnsupervisedR&R: Unsupervised Pointcloud Registration via Differentiable Rendering This repository holds all the code and data for our recent work on

118 Dec 6, 2022

Python Implementation of the CoronaWarnApp (CWA) Event Registration

Python implementation of the Corona-Warn-App (CWA) Event Registration This is an implementation of the Protocol used to generate event and location QR

17 Oct 5, 2022

the code of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021)

RMA-Net This repo is the implementation of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021). Paper

205 Nov 9, 2022

[CVPR'21] Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration

Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration This repository contains the implementation of our paper Locally Aware Pi

70 Dec 19, 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

93 Dec 21, 2022

A robust pointcloud registration pipeline based on correlation.

PHASER: A Robust and Correspondence-Free Global Pointcloud Registration Ubuntu 18.04+ROS Melodic: Overview Pointcloud registration using correspondenc

101 Dec 1, 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

42 Jul 25, 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

80 Dec 15, 2022

Comments

Rigid Transformation are not defined in RigidIRNet

Respected, Kindly, provide the solution, how to create the class of Rigid transformer in transformer.py. Create the class of RigidIRNet in "https://github.com/BDdeVos/TorchIR/blob/main/torchir/networks/globalnet.py" .

Thanks.

opened by Paluck1Arora2 0
No networks Module on PyPi

PyPi Package torchir==0.1 Does Not Include Networks Package Reproduce: pip3 install torchir in python: from torchir.networks.globalnet import ConvBlock

opened by pweibert 0
Using color images as input for the network

Hello,

I am trying to adapt your work for the alignment of ophthalmological retina images using 3-channel color images. Which changes are necessary to use the framework for this kind of data?

Kind regards and thanks for your work on image registration!

opened by AgenoDrei 0
Rigid transformation parameters not equal

Hi, I used torchio to generate some moved 3d image ,which by applying the translation(pixelwise) and rotation(degree) to the still image(without motion), and use the network RigidIRNet to estimate this translation and rotation parameter.

Then I found that although the NCC loss are decreased and the warped image is acceptable, the estimated parameter have a big different compared with the one that I appied beforehand.

May I ask why is the issue for this weird situation ?

opened by jeremysong1106 0

Releases(version_01)

version_01(Nov 15, 2021)

Source code(tar.gz)
Source code(zip)

Owner

Bob de Vos

GitHub Repository

Plover-tapey-tape: an alternative to Plover’s built-in paper tape

plover-tapey-tape plover-tapey-tape is an alternative to Plover’s built-in paper

7 May 29, 2022

This is an implementation of PIFuhd based on Pytorch

Open-PIFuhd This is a unofficial implementation of PIFuhd PIFuHD: Multi-Level Pixel-Aligned Implicit Function forHigh-Resolution 3D Human Digitization

235 Dec 19, 2022

CR-Fill: Generative Image Inpainting with Auxiliary Contextual Reconstruction. ICCV 2021

182 Dec 20, 2022

PyTorch implementation of the paper Ultra Fast Structure-aware Deep Lane Detection

1.4k Jan 06, 2023

CVPR '21: In the light of feature distributions: Moment matching for Neural Style Transfer

In the light of feature distributions: Moment matching for Neural Style Transfer (CVPR 2021) This repository provides code to recreate results present

49 Oct 13, 2022

The PASS dataset: pretrained models and how to get the data - PASS: Pictures without humAns for Self-Supervised Pretraining

249 Dec 22, 2022

On Generating Extended Summaries of Long Documents

ExtendedSumm This repository contains the implementation details and datasets used in On Generating Extended Summaries of Long Documents paper at the

76 Sep 05, 2022

PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems

PowerGridworld provides users with a lightweight, modular, and customizable framework for creating power-systems-focused, multi-agent Gym environments that readily integrate with existing training fr

37 Dec 17, 2022

Generating Band-Limited Adversarial Surfaces Using Neural Networks

Generating Band-Limited Adversarial Surfaces Using Neural Networks This is the official repository of the technical report that was published on arXiv

3 Jul 26, 2022

simple artificial intelligence utilities

Simple AI Project home: http://github.com/simpleai-team/simpleai This lib implements many of the artificial intelligence algorithms described on the b

921 Dec 08, 2022

CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation (ACMMM'21 Oral Paper)

CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation (ACMMM'21 Oral Paper) (Accepted for oral presentation at ACM

1 Nov 12, 2021

Tgbox-bench - Simple TGBOX upload speed benchmark

TGBOX Benchmark This script will benchmark upload speed to TGBOX storage. Build

1 Jan 09, 2022

This project is based on RIFE and aims to make RIFE more practical for users by adding various features and design new models

CPM 项目描述 CPM（Chinese Pretrained Models）模型是北京智源人工智能研究院和清华大学发布的中文大规模预训练模型。官方发布了三种规模的模型，参数量分别为109M、334M、2.6B，用户需申请与通过审核，方可下载。由于原项目需要考虑大模型的训练和使用，需要安装较为复杂

190 Jan 08, 2023