# DIPLI: Deep Image Prior Lucky Imaging for Blind Astronomical Image Restoration

arXiv: https://arxiv.org/abs/2503.15984 · HTML: https://mlsanity.com/paper/2503.15984/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 64 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 23 of 23)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Deep Learning Techniques for Inverse Problems in Imaging](https://mlsanity.com/paper/2005.06001/) (2020)
- [Recurrent Video Restoration Transformer with Guided Deformable Attention](https://mlsanity.com/paper/2206.02146/) (2022)
- [Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks](https://mlsanity.com/paper/1810.03982/) (2018)
- [A Review of Convolutional Neural Networks for Inverse Problems in Imaging](https://mlsanity.com/paper/1710.04011/) (2017)
- [Blind Video Temporal Consistency via Deep Video Prior](https://mlsanity.com/paper/2010.11838/) (2020)
- [A Bayesian Perspective on the Deep Image Prior](https://mlsanity.com/paper/1904.07457/) (2019)
- [End-to-End Learning of Motion Representation for Video Understanding](https://mlsanity.com/paper/1804.00413/) (2018)
- [DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models](https://mlsanity.com/paper/2407.01519/) (2024)
- [Deep Matching Prior: Test-Time Optimization for Dense Correspondence](https://mlsanity.com/paper/2106.03090/) (2021)
- [Guided Deep Decoder: Unsupervised Image Pair Fusion](https://mlsanity.com/paper/2007.11766/) (2020)
- [NAS-DIP: Learning Deep Image Prior with Neural Architecture Search](https://mlsanity.com/paper/2008.11713/) (2020)
- [Untrained Graph Neural Networks for Denoising](https://mlsanity.com/paper/2109.11700/) (2021)
- [Neural Architecture Search for Deep Image Prior](https://mlsanity.com/paper/2001.04776/) (2020)
- [Deep Variational Network Toward Blind Image Restoration](https://mlsanity.com/paper/2008.10796/) (2020)
- [ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior](https://mlsanity.com/paper/2111.15362/) (2021)
- [Convergence Analysis of Stochastic Gradient Descent with MCMC Estimators](https://mlsanity.com/paper/2303.10599/) (2023)
- [A Projectional Ansatz to Reconstruction](https://mlsanity.com/paper/1907.04675/) (2019)

## Abstract (arXiv)

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 labeled training datasets, which are rarely available in astrophotography. Deep Image Prior (DIP) bypasses this constraint by performing unsupervised optimization on a single image without training data; however, DIP often suffers from overfitting, artifact generation, and instability. This work proposes DIPLI - a framework designed specifically for resolved, high-contrast astronomical targets that shifts from single-frame to multi-frame processing using the Back Projection technique, combined with dense optical flow estimation via the TVNet model, and replaces deterministic predictions with Monte Carlo estimation obtained through Stochastic Gradient Langevin Dynamics (SGLD). A comprehensive evaluation compares the method against the original DIP, the transformer-based model RVRT, and the diffusion-based model DiffIR2VR-Zero on synthetic data with ground truth, while comparing qualitatively against Lucky Imaging on real astronomical data. On synthetic datasets, DIPLI achieves the best perceptual fidelity scores (LPIPS in 12/12 and DISTS in 10/12 scenarios), while the diffusion-based DiffIR2VR-Zero achieves the best pixel-level distortion scores (PSNR in 9/12 and SSIM in 8/12 scenarios), consistent with the well-known perceptual-distortion trade-off in image restoration. Compared to classical Lucky Imaging, the model requires far fewer input frames (7-13 versus thousands) and avoids the need for early stopping that limits standard DIP. Qualitative evaluation on real-world data of resolved solar-system objects, where ground truth is unavailable and domain shifts typically hinder generalization, suggests that the method appears to preserve fine detail while suppressing noise and artifacts.