A denoising diffusion probabilistic model synthesises galaxies that are qualitatively and physically indistinguishable from the real thing.

Last update: Dec 20, 2022

Overview

Realistic galaxy simulation via score-based generative models

Official code for 'Realistic galaxy simulation via score-based generative models'. We use a score-based generative model to produce realistic galaxy images. This implementation is based off of Phil Wang's PyTorch version which is in turn transcribed from Jonathan Ho's official Tensorflow version here.

Below are some outputs from our model. Half of these galaxies are real and half are generated. Check out the paper for the answer key.

Running the code

I will be adding full instructions to train and infer with this code within the next couple of days.

This Galaxy/APOD Does Not Exist

More galaxies can be found here.

We also used a DDPM to generate fake Astronomy Picture Of the Day imagery. Check it out.

Citing

If you find this work useful please consider citing our paper:

@article{smith2021,
    title={Realistic galaxy image simulation via score-based generative models},
    author={Michael J. Smith and James E. Geach and Ryan A. Jackson and Nikhil Arora and Connor Stone and St{\'{e}}ephane Courteau},
    journal = {arXiv e-prints},
    year={2021},
    eprint = {2111.01713}
}

Also be sure to check out Jonathan Ho's implementation here:

@article{ho2020,
    author = {{Ho}, Jonathan and {Jain}, Ajay and {Abbeel}, Pieter},
    title = "{Denoising Diffusion Probabilistic Models}",
    journal = {arXiv e-prints},
    year = 2020,
    eprint = {2006.11239},
}

And Jascha Sohl-Dickstein's original DDPM paper:

@article{sohl-dickstein2015,
    author = {{Sohl-Dickstein}, Jascha and {Weiss}, Eric A. and {Maheswaranathan}, Niru and {Ganguli}, Surya},
    title = "{Deep Unsupervised Learning using Nonequilibrium Thermodynamics}",
    journal = {arXiv e-prints},
    year = 2015,
    eprint = {1503.03585}
}

Contributing

AstroDDPM is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

AstroDDPM is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public License for more details.

You should have received a copy of the GNU Affero General Public License along with AstroDDPM. If not, see https://www.gnu.org/licenses/.

Comments

Could you share the dataset?

I tried to use your download script to download the images, but found that many images are empty (0 bytes), and by manually visiting the URL I got "500 server error" or "301 Moved permanently". Eventually only around ~~2k~~6k images were downloaded successfully. (They were converted to around 2k npy files.)

So, I wonder could you please share the images you downloaded? I guess if every user downloads their own copy of the images, it also adds load to the server.

Thank you so much!

opened by askerlee 6

Official PyTorch implementation for FastDPM, a fast sampling algorithm for diffusion probabilistic models

Official PyTorch implementation for "On Fast Sampling of Diffusion Probabilistic Models". FastDPM generation on CIFAR-10, CelebA, and LSUN datasets. S

68 Dec 26, 2022

Official repository for "Restormer: Efficient Transformer for High-Resolution Image Restoration". SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

Restormer: Efficient Transformer for High-Resolution Image Restoration Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan,

906 Dec 30, 2022

QuakeLabeler is a Python package to create and manage your seismic training data, processes, and visualization in a single place — so you can focus on building the next big thing.

QuakeLabeler Quake Labeler was born from the need for seismologists and developers who are not AI specialists to easily, quickly, and independently bu

15 Nov 4, 2022

Code for the paper One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation, CVPR 2021.

One Thing One Click One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation (CVPR2021) Code for the paper One Thi

44 Dec 12, 2022

The trained model and denoising example for paper : Cardiopulmonary Auscultation Enhancement with a Two-Stage Noise Cancellation Approach

1 Jan 18, 2022

Official codebase for running the small, filtered-data GLIDE model from GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

GLIDE This is the official codebase for running the small, filtered-data GLIDE model from GLIDE: Towards Photorealistic Image Generation and Editing w

2.9k Jan 4, 2023

Pytorch Implementation of DiffSinger: Diffusion Acoustic Model for Singing Voice Synthesis (TTS Extension)

A denoising diffusion probabilistic model synthesises galaxies that are qualitatively and physically indistinguishable from the real thing.

Related tags

Overview

Realistic galaxy simulation via score-based generative models

Running the code

This Galaxy/APOD Does Not Exist

Citing

Contributing

You might also like...

Official PyTorch implementation for FastDPM, a fast sampling algorithm for diffusion probabilistic models

Official repository for "Restormer: Efficient Transformer for High-Resolution Image Restoration". SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.

QuakeLabeler is a Python package to create and manage your seismic training data, processes, and visualization in a single place — so you can focus on building the next big thing.

Code for the paper One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation, CVPR 2021.

The trained model and denoising example for paper : Cardiopulmonary Auscultation Enhancement with a Two-Stage Noise Cancellation Approach

Official codebase for running the small, filtered-data GLIDE model from GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models.

Pytorch Implementation of DiffSinger: Diffusion Acoustic Model for Singing Voice Synthesis (TTS Extension)

Implementation of GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation (ICLR 2022).

Implementation of the final project of the course DDA6309 Probabilistic Graphical Model

Comments

Could you share the dataset?

Releases(v1.0.0)

v1.0.0(Mar 26, 2022)

Owner

Michael Smith

Molecular AutoEncoder in PyTorch

Official implementation for ICDAR 2021 paper "Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer"

Implementation of gMLP, an all-MLP replacement for Transformers, in Pytorch

[AAAI-2022] Official implementations of MCL: Mutual Contrastive Learning for Visual Representation Learning

Efficient semidefinite bounds for multi-label discrete graphical models.

Code, final versions, and information on the Sparkfun Graphical Datasheets

Official implementation of NeurIPS 2021 paper "One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective"

This repo provides the official code for TransBTS: Multimodal Brain Tumor Segmentation Using Transformer (https://arxiv.org/pdf/2103.04430.pdf).

Points2Surf: Learning Implicit Surfaces from Point Clouds (ECCV 2020 Spotlight)

Official implementation for "Style Transformer for Image Inversion and Editing" (CVPR 2022)

Real-time Object Detection for Streaming Perception, CVPR 2022

PASSL包含 SimCLR，MoCo，BYOL，CLIP等基于对比学习的图像自监督算法以及 Vision-Transformer，Swin-Transformer，BEiT，CVT，T2T，MLP_Mixer等视觉Transformer算法

DARTS-: Robustly Stepping out of Performance Collapse Without Indicators

Dynamic Slimmable Network (CVPR 2021, Oral)

This is the code for the paper "Contrastive Clustering" (AAAI 2021)

A light-weight image labelling tool for Python designed for creating segmentation data sets.

[CVPR 2021] Teachers Do More Than Teach: Compressing Image-to-Image Models (CAT)

Compare outputs between layers written in Tensorflow and layers written in Pytorch

Reproducing-BowNet: Learning Representations by Predicting Bags of Visual Words

Clairvoyance: a Unified, End-to-End AutoML Pipeline for Medical Time Series