ASTRA-SR is a blind single‑frame restoration framework designed for ground‑based planetary imaging, addressing atmospheric turbulence, sensor noise, and limited sampling. It is trained on a physics‑grounded synthetic dataset that uses high‑dynamic‑range spacecraft RAW observations as clean sources and synthesizes low‑resolution inputs with realistic turbulence, PSFs, and noise. The method first produces a noise‑suppressed but blur‑retaining low‑resolution image, then restores spatial structure via multiscale processing and refines high‑resolution detail with serial spatial‑amplitude refinement, achieving a 0.49 dB PSNR gain over the strongest baseline approaches.
arXiv:2601.23276v4 Announce Type: replace-cross Abstract: Astronomical imaging remains noise-limited under practical observing conditions. Standard calibration pipelines remove structured artifacts b...
arXiv:2609.07012v1 Announce Type: cross Abstract: Pushbroom satellite imaging couples limited spatial resolution with platform attitude instability. Platform jitter produces spatially varying motion...
arXiv:2610.23454v1 Announce Type: new Abstract: Atmospheric turbulence degrades image quality in long-range imaging. The degradation is generally modeled with two spatio-temporally varying components...
arXiv:2605.21440v2 Announce Type: replace Abstract: Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing...
arXiv:2602. 10330v3 Announce Type: replace-cross Abstract: Context: The characterization of exoplanetary atmospheres has been transformed by the James Webb Space Telescope (JWST), whose infrared sensitivity enables transmission spectroscopy at unprecedented precision.
The paper introduces a deep‑learning pipeline that improves detection of faint moving objects in optical space situational awareness imagery. It combines a Tiny‑U‑Net segmentation network to mask stars with a partial‑convolution variational autoencoder (astro‑VAE) that learns background statistics and performs context‑aware inpainting. The reconstructed, star‑free backgrounds are used as a preprocessing step before detection, and when integrated with a shift‑and‑stack scheme, the method shows high‑fidelity background reconstruction and significant enhancement of moving‑target detectability in real ground‑based telescope data.
arXiv:2602.19736v3 Announce Type: replace Abstract: Diffusion models now give the best perceptual quality in super-resolution (SR), but their architecture and training confine them to small fixed cro...
The study demonstrates that a wide‑activation deep super‑resolution (WDSR) network can learn to reconstruct unseen two‑dimensional homogeneous isotropic turbulence fields from overlapping patches of a single high‑resolution realization. By training exclusively on these patches, the model achieves extreme super‑resolution factors of x32 and x64, accurately recovering coherent vortical structures and fine‑scale features better than conventional interpolation. Spectral and statistical analyses confirm improved high‑wavenumber energy recovery and multiscale flow characteristics, and comparisons with models trained on multiple full snapshots highlight the advantage of exploiting spatial redundancy within a single realization.
The paper introduces PGL-Net, a lightweight physics-inspired network for real‑world single image dehazing. It decouples the task into global distribution rectification and local structural refinement, using a Physics‑Inspired Affine Fusion module for global alignment and a Degradation‑Aware Modulation block for adaptive detail restoration. Experiments show that PGL‑Net, especially its Tiny variant, outperforms recent state‑of‑the‑art methods in PSNR and downstream object detection while reducing inference latency by over tenfold.
IR275K is a curated benchmark for infrared multi‑frame super‑resolution, comprising 594 video sequences and 275,196 frames with train/validation/test splits and a reproducible x4 evaluation protocol. It evaluates seven learned baselines, the CGMamba reference model, and bicubic interpolation under both bicubic degradation and synthetic mixed sensor noise, revealing that EDVR performs best under bicubic degradation while MSDTGP excels under mixed sensor noise. Ablations with CGMamba demonstrate that using real neighboring frames improves PSNR by about 1 dB compared to center‑frame repetition, and that center‑frame conditioning also benefits reconstruction across conditions.
arXiv:2609.35966v1 Announce Type: cross Abstract: Radio-interferometric images are reconstructed from sparsely sampled visibilities, and CLEAN-based imaging can struggle with spatial filtering, compl...
arXiv:2606. 02661v1 Announce Type: cross Abstract: Accurate precipitation nowcasting is vital for disaster mitigation, but deep learning methods face a key trade-off: regression models produce over-smoothed, spectrally decaying predictions that blur convective details and violate turbulence power laws; diffusion models generate realistic yet unanchored hallucinations lacking physical grounding.