A deep learning calibration framework, the Multi-Feature Fused Network (MFF-Net), is introduced, which takes instrumental magnitude, color, and pixel coordinates as input and learns a single nonlinear correction that jointly captures their coupled dependencies.
Abstract
Photometric calibration of digitized photographic plates is commonly modeled with separable magnitude-, color-, and position-dependent terms, but this separability can break down when image quality varies across the field in a magnitude-dependent way, leaving coupled spatial systematics in the residuals. We introduce a deep learning calibration framework, the Multi-Feature Fused Network (MFF-Net), which takes instrumental magnitude, color, and pixel coordinates as input and learns a single nonlinear correction that jointly captures their coupled dependencies. Tests on 1200 digitized Chinese plates show that MFF-Net consistently outperforms the MYX25 method, improving the 5th–95th percentile precision from 0.11–0.26 mag to 0.08–0.18 mag and delivering an approximately factor-of-2 gain for bright sources. The learned correction largely removes the magnitude–position coupling seen in postcalibration residual maps, enabling higher-precision plate photometry and more reliable use of large historical plate archives.
An AI-assisted processing framework is presented that integrates subpixel distortion correction, deep learning-based noise identification, two-dimensional fiber-spot reconstruction, and spectral de blending in fiber-fed multi-object astronomical spectroscopy.
Wei-Min Sun, Jin-Hui Cui, Dong-Sheng Hu et al.· Astronomical Telescopes + In...· 0 citations
An enhancement pipeline that operates entirely within classical signal processing is proposed, providing a transparent alternative to black-box machine learning methods while remaining practical on standard personal computers.
Swarnajit Bhattacharya· Asian journal of applied sci...· 0 citations
DensePol is introduced, a high-redundancy RGB--polarization dataset based on Division-of-Time (DoT) acquisition, and a deterministic diffusion-based RGB-to-polarization framework with cyclic AoLP representation and a local DoLP refiner, which demonstrates improved polarization prediction and downstream surface-normal e...
Param Sangani, Ahmad Moori, Erik Blasch et al.· 0 citations
It is concluded that future industrial deployment on edge-computing platforms will rely on a synergy between lightweight network architectures and multi-sensor fusion and self-supervised frameworks.
Deep learning is widely used to analyze galaxy images, and the reconstruction loss determines which image features a model prioritizes during training. Mean squared error (MSE) and mean absolute error (MAE) correspond to homoscedastic Gaussian and Laplace likelihoods, respectively, whereas the inverse-variance-weighted...
Ren-Hao Ye, Shi-Yin Shen, Quan-Feng Xu· Universe· 0 citations
We investigate Deep Image Prior neural networks for image reconstruction from sparse long-baseline interferometric data. The sky brightness distribution is parameterized as the output of an untrained U-Net-like convolutional generator, whose parameters are optimized independently for each data set by minimizing a loss...
J. Sánchez-Bermudez· Astronomical Telescopes + In...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.