Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging

by   Hao Wang, et al.

Deep learning has transformed computational imaging, but traditional pixel-based representations limit their ability to capture continuous, multiscale details of objects. Here we introduce a novel Local Conditional Neural Fields (LCNF) framework, leveraging a continuous implicit neural representation to address this limitation. LCNF enables flexible object representation and facilitates the reconstruction of multiscale information. We demonstrate the capabilities of LCNF in solving the highly ill-posed inverse problem in Fourier ptychographic microscopy (FPM) with multiplexed measurements, achieving robust, scalable, and generalizable large-scale phase retrieval. Unlike traditional neural fields frameworks, LCNF incorporates a local conditional representation that promotes model generalization, learning multiscale information, and efficient processing of large-scale imaging data. By combining an encoder and a decoder conditioned on a learned latent vector, LCNF achieves versatile continuous-domain super-resolution image reconstruction. We demonstrate accurate reconstruction of wide field-of-view, high-resolution phase images using only a few multiplexed measurements. LCNF robustly captures the continuous object priors and eliminates various phase artifacts, even when it is trained on imperfect datasets. The framework exhibits strong generalization, reconstructing diverse objects even with limited training data. Furthermore, LCNF can be trained on a physics simulator using natural images and successfully applied to experimental measurements on biological samples. Our results highlight the potential of LCNF for solving large-scale inverse problems in computational imaging, with broad applicability in various deep-learning-based techniques.


page 7

page 8

page 9

page 11

page 29

page 30

page 31

page 33


GedankenNet: Self-supervised learning of hologram reconstruction using physics consistency

The past decade has witnessed transformative applications of deep learni...

Physical model simulator-trained neural network for computational 3D phase imaging of multiple-scattering samples

Recovering 3D phase features of complex, multiple-scattering biological ...

3D Phase Retrieval at Nano-Scale via Accelerated Wirtinger Flow

Imaging 3D nano-structures at very high resolution is crucial in a varie...

On the interplay between physical and content priors in deep learning for computational imaging

Deep learning (DL) has been applied extensively in many computational im...

Memory-efficient Learning for Large-scale Computational Imaging

Computational imaging systems jointly design computation and hardware to...

Agile wide-field imaging with selective high resolution

Wide-field and high-resolution (HR) imaging is essential for various app...

Please sign up or login with your details

Forgot password? Click here to reset