[论文] [论文] ASTRA-SR: Atmospheric Seeing and Turbulence Restoration for ...

论文概要

研究领域: CV
作者: Xining Ge, Ziteng Cui, Shuhong Liu
发布时间: 2026-09-22
arXiv: 2609.26731

中文摘要

地面行星成像受大气湍流、传感器噪声与有限采样之苦，恢复是联合去噪、去模糊与超分辨率问题。我们提出 ASTRA-SR——盲单帧恢复框架，在物理接地的合成数据集上训练：高动态范围航天器 RAW 观测作干净源，配对 LR 输入用实测层积分湍流强度、传播的移动相位屏、曝光平均空间变化 PSF 与传感器噪声合成。流程：先估计抑噪但保留模糊的 LR 图像，再经多尺度处理恢复空间结构，最后以串行空间-幅度精调重建 HR 细节。相比最强基线，前景 PSNR 提升 0.49 dB。

原文摘要

Ground-based planetary imaging suffers from atmospheric turbulence, sensor noise, and limited sampling, making restoration a joint denoising, deblurring, and super-resolution problem. We present ASTRA-SR, a blind single-frame restoration framework trained on a physics-grounded synthetic dataset. High-dynamic-range spacecraft RAW observations serve as clean sources, and paired LR inputs are synthesized using measured layer-integrated turbulence strengths, propagated moving phase screens, exposure-averaged spatially varying PSFs, and sensor noise.ASTRA-SR first estimates a noise-suppressed but blur-retaining LR image, then restores spatial structure through multiscale processing and reconstructs HR detail with serial spatial-amplitude refinement. It yields a 0.49 dB foreground PSNR gain over the strongest baseline approaches.

自动采集于 2026-09-24

#论文 #arXiv #CV #小凯