Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
Not on the map. Why?
Abstract (arXiv)
Image-to-image translation with Deep Learning neural networks, particularly with Generative Adversarial Networks (GANs), is one of the most powerful methods for simulating astronomical images. However, current work is limited to utilizing paired images with supervised translation, and there has been rare discussion on reconstructing noise background that encodes instrumental and observational effects. These limitations might be harmful for subsequent scientific applications in astrophysics. Therefore, we aim to develop methods for using unpaired images and preserving noise characteristics in image translation. In this work, we propose a two-way image translation model using GANs that exploits both paired and unpaired images in a semi-supervised manner, and introduce a noise emulating module that is able to learn and reconstruct noise characterized by high-frequency features. By experimenting on multi-band galaxy images from the Sloan Digital Sky Survey (SDSS) and the Canada France Hawaii Telescope Legacy Survey (CFHT), we show that our method recovers global and local properties effectively and outperforms benchmark image translation models. To our best knowledge, this work is the first attempt to apply semi-supervised methods and noise reconstruction techniques in astrophysical studies.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 33 references that are in the map. First posted on arXiv 19 Jan 2021.
Builds on
25 of 33 references.
References · 25
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
- 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
- 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
- 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 858
- 2017Wasserstein GANcited by 635
- 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
- 2016Adversarial Feature Learningcited by 350
- 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
13 more
- 2017Learning to Discover Cross-Domain Relations with Generative Adversarial Networkscited by 278
- 2016Adversarially Learned Inferencecited by 216
- 2016Coupled Generative Adversarial Networkscited by 216
- 2019ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentationcited by 105
- 2018Distribution Matching Losses Can Hallucinate Features in Medical Image Translationcited by 99
- 2018Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Datacited by 76
- 2019TraVeLGAN: Image-to-image Translation by Transformation Vector Learningcited by 35
- 2017XGAN: Unsupervised Image-to-Image Translation for Many-to-Many Mappingscited by 27
- 2017Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limitcited by 26
- 2017CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networkscited by 17
- 2018Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networkscited by 8
- 2018Deblending galaxy superpositions with branched generative adversarial networkscited by 3
- 2018Denoising Weak Lensing Mass Maps with Deep Learningcited by 1
Built on by
Not cited yet.