Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
arXiv:2101.07389 · doi:10.1109/ICPR48806.2021.9412143
Abstract
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.
arXiv commentAccepted at ICPR 2020
References in corpus (21)
- Adam: A Method for Stochastic Optimization
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Conditional Generative Adversarial Nets
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- The Eleventh and Twelfth Data Releases of the Sloan Digital Sky Survey: Final Data from SDSS-III
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
- Adversarial Feature Learning
- Adversarially Learned Inference
- Preparing Red-Green-Blue (RGB) Images from CCD Data
- Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
- Distribution Matching Losses Can Hallucinate Features in Medical Image Translation
- Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
- Photometric redshifts from SDSS images using a Convolutional Neural Network
- The CFHT Legacy Survey: stacked images and catalogs
- CosmoGAN: creating high-fidelity weak lensing convergence maps using Generative Adversarial Networks
- Coupled Generative Adversarial Networks
- Deblending galaxy superpositions with branched generative adversarial networks
- Forging new worlds: high-resolution synthetic galaxies with chained generative adversarial networks
- Denoising Weak Lensing Mass Maps with Deep Learning
- ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation
- RadioGAN - Translations between different radio surveys with generative adversarial networks