Contemporary image restoration and super-resolution techniques effectively harness deep neural networks, markedly outperforming traditional methods. However, astrophotography presents unique challenges for deep learning due to limited training data. This work explores hybrid strategies, such as the Deep Image Prior (DIP) model, which facilitates blind training but is susceptible to overfitting, artifact generation, and instability when handling noisy images. We propose enhancements to the DIP model's baseline performance through several advanced techniques. First, we refine the model to process multiple frames concurrently, employing the Back Projection method and the TVNet model. Next, we adopt a Markov approach incorporating Monte Carlo estimation, Langevin dynamics, and a variational input technique to achieve unbiased estimates with minimal variance and counteract overfitting effectively. Collectively, these modifications reduce the likelihood of noise learning and mitigate loss function fluctuations during training, enhancing result stability. We validated our algorithm across multiple image sets of astronomical and celestial objects, achieving performance that not only mitigates limitations of Lucky Imaging, a classical computer vision technique that remains a standard in astronomical image reconstruction but surpasses the original DIP model, state of the art transformer- and diffusion-based models, underscoring the significance of our improvements.

If you'd asked me 5 years ago if I thought a smartphone would ever be able to capture a decent image of the Milky Way my answer would have been a resounding no. With tiny sensors and small lenses that aren't capable of guiding much light onto the sensor there's no way they're ever going to be much use in such low-light conditions, right? Well, ask me the same question today and my answer would be a lot different. By using techniques such as stacking multiple images for noise reduction, or using artificial intelligence (AI) to improve the image's look, smartphones are becoming scarily capable of producing decent astrophotographs. I asked my followers on Instagram to send in their smartphone astrophotography and I was blown away!