Image super-resolution is a technique of enhancing the resolution of an image where a high-resolution (HR) image is reconstructed from a low-resolution (LR) image. In this Letter, we apply two novel deep learning models (residual attention model and progressive GAN model) for enhancing Solar Dynamics Observatory (SDO)/Helioseismic and Magnetic Imager (HMI) magnetograms. For this, we consider line-of-sight (LOS) magnetograms taken by SDO/HMI as output and their degraded ones with 4 × 4 binning as input. Deep learning networks try to find internal relationships between LR and HR images from the given input and the corresponding output image. We consider SDO/HMI magnetograms from 2014 May to August for training, from 2014 October to December for validation, and 2015 January to March for test. We find that the deep learning models generate higher-quality results than the bicubic interpolation in terms of visual aspects and metrics. We apply this model to a full-resolution SDO/HMI magnetogram and then compare the generated magnetogram with the corresponding Hinode/The Solar Optical Telescope Narrowband Filtergrams (NFI) magnetogram. This comparison shows that the generated magnetogram is consistent with the Hinode one with a high correlation (CC: 0.94) and a high similarity (SSIM: 0.93), which are better than the bicubic method.

No abstract

This study is the first attempt to generate a three-dimensional (3D) coronal electron density distribution based on the pix2pixHD model, whose computing time is much shorter than that of the magnetohydrodynamic (MHD) simulation. For this, we consider photospheric solar magnetic fields as input, and electron density distribution simulated with the MHD Algorithm outside a Sphere (MAS) at a given solar radius is taken as output. We consider 155 pairs of Carrington rotations as inputs and outputs from 2010 June to 2022 April for training and testing. We train 152 deep-learning models for 152 solar radii, which are taken up to 30 solar radii. The artificial intelligence (AI) generated 3D electron densities from this study are quite consistent with the simulated ones from lower radii to higher radii, with an average correlation coefficient 0.97. The computing time of testing data sets up to 30 solar radii of 152 deep-learning models is about 45.2 s using the NVIDIA TITAN XP graphics-processing unit, which is much less than the typical simulation time of MAS. We find that the synthetic coronagraphic images estimated from the deep-learning models are similar to the Solar Heliospheric Observatory (SOHO)/Large Angle and Spectroscopic Coronagraph C3 coronagraph data, especially during the solar minimum period. The AI-generated coronal density distribution from this study can be used for space weather models on a near-real-time basis.

No abstract

The three-dimensional (3D) symmetry shape plays a critical role in the reconstruction and recognition of 3D objects under occlusion or partial viewpoint observation. Symmetry structure prior is particularly useful in recovering missing or unseen parts of an object. In this work, we propose Sym3DNet for single-view 3D reconstruction, which employs a three-dimensional reflection symmetry structure prior of an object. More specifically, Sym3DNet includes 2D-to-3D encoder-decoder networks followed by a symmetry fusion step and multi-level perceptual loss. The symmetry fusion step builds flipped and overlapped 3D shapes that are fed to a 3D shape encoder to calculate the multi-level perceptual loss. Perceptual loss calculated in different feature spaces counts on not only voxel-wise shape symmetry but also on the overall global symmetry shape of an object. Experimental evaluations are conducted on both large-scale synthetic 3D data (ShapeNet) and real-world 3D data (Pix3D). The proposed method outperforms state-of-the-art approaches in terms of efficiency and accuracy on both synthetic and real-world datasets. To demonstrate the generalization ability of our approach, we conduct an experiment with unseen category samples of ShapeNet, exhibiting promising reconstruction results as well.