Towards Lensless Image Deblurring with Prior-Embedded Implicit Neural Representations in the Low-Data Regime
This addresses the problem of enabling ultra-thin imaging systems for computational imaging applications, though it appears incremental as it builds on untrained neural network paradigms.
The paper tackles lensless image deblurring by using implicit neural representations with prior-embedded optimization, achieving reconstructions without prior training and showing superior performance in low-data regimes compared to existing methods.
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.