Towards Lensless Image Deblurring with Prior-Embedded Implicit Neural Representations in the Low-Data Regime

TL;DR

This paper introduces a novel lensless image deblurring method using prior-embedded implicit neural representations, enabling high-quality reconstructions in low-data regimes without prior training.

Contribution

It is the first to leverage implicit neural representations for lensless image deblurring, combining untrained iterative optimization with prior embedding for improved performance.

Findings

Outperforms existing untrained and low-shot methods

Achieves high-quality reconstructions without prior training

Speeds up convergence compared to traditional methods

Abstract

The field of computational imaging has witnessed a promising paradigm shift with the emergence of untrained neural networks, offering novel solutions to inverse computational imaging problems. While existing techniques have demonstrated impressive results, they often operate either in the high-data regime, leveraging Generative Adversarial Networks (GANs) as image priors, or through untrained iterative reconstruction in a data-agnostic manner. This paper delves into lensless image reconstruction, a subset of computational imaging that replaces traditional lenses with computation, enabling the development of ultra-thin and lightweight imaging systems. To the best of our knowledge, we are the first to leverage implicit neural representations for lensless image deblurring, achieving reconstructions without the requirement of prior training. We perform prior-embedded untrained iterative optimization to enhance reconstruction performance and speed up convergence, effectively bridging the gap between the no-data and high-data regimes. Through a thorough comparative analysis encompassing various untrained and low-shot methods, including under-parameterized non-convolutional methods and domain-restricted low-shot methods, we showcase the superior performance of our approach by a significant margin.