DIPLI: Deep Image Prior Lucky Imaging for Blind Astronomical Image Restoration
This work addresses a practical problem for astronomers by enabling robust image restoration with limited data, though it appears incremental as it builds on existing Deep Image Prior techniques.
The paper tackles the problem of astronomical image restoration without large training datasets by proposing DIPLI, a multi-frame training framework that combines Back Projection, optical flow estimation, and Monte Carlo estimation. The method consistently outperforms baselines like Lucky Imaging, DIP, RVRT, and DiffIR2VR-Zero on synthetic datasets for metrics such as SSIM, PSNR, LPIPS, and DISTS, and maintains high quality on real-world data with fewer input images and reduced overfitting.
Modern image restoration and super-resolution methods utilize deep learning due to its superior performance compared to traditional algorithms. However, deep learning typically requires large training datasets, which are rarely available in astrophotography. Deep Image Prior (DIP) bypasses this constraint by performing blind training on a single image. Although effective in some cases, DIP often suffers from overfitting, artifact generation, and instability. To overcome these issues and improve general performance, this work proposes DIPLI - a framework that shifts from single-frame to multi-frame training using the Back Projection technique, combined with optical flow estimation via the TVNet model, and replaces deterministic predictions with unbiased Monte Carlo estimation obtained through Langevin dynamics. A comprehensive evaluation compares the method against Lucky Imaging, a classical computer vision technique still widely used in astronomical image reconstruction, DIP, the transformer-based model RVRT, and the diffusion-based model DiffIR2VR-Zero. Experiments on synthetic datasets demonstrate consistent improvements, with the method outperforming baselines for SSIM, PSNR, LPIPS, and DISTS metrics in the majority of cases. In addition to superior reconstruction quality, the model also requires far fewer input images than Lucky Imaging and is less prone to overfitting or artifact generation. Evaluation on real-world astronomical data, where domain shifts typically hinder generalization, shows that the method maintains high reconstruction quality, confirming practical robustness.