Learning Binary Sampling Patterns for Single-Pixel Imaging using Bilevel Optimisation

Serban Cristian Tudosie, Alexander Denker, Zeljko Kereta, Simon Arridge

Keywords: single-pixel imaging, bilevel optimization, binary optimization, microscopy

TL;DR: We make use of the Straight-Through Estimator, bilevel optimisation, and Total Deep Variation to design binary sampling patterns for single-pixel imaging.

Abstract: Single-Pixel Imaging enables reconstructing objects using a single detector through sequential illuminations with structured light patterns. We propose a bilevel optimisation method for learning task-specific, binary illumination patterns, optimised for applications like single-pixel fluorescence microscopy. We address the non-differentiable nature of binary pattern optimisation using the Straight-Through Estimator and leveraging a Total Deep Variation regulariser in the bilevel formulation. We demonstrate our method on the CytoImageNet microscopy dataset and show that learned patterns achieve superior reconstruction performance compared to baseline methods, especially in highly undersampled regimes.

Submission Number: 1