Deep Feature-specific Imaging

TL;DR

DeepFSI is a novel end-to-end framework that learns optimal measurement masks for photon-limited imaging, improving classification accuracy and robustness under Poisson noise compared to traditional PCA-based methods.

Contribution

It introduces DeepFSI, enabling neural networks to learn measurement masks directly under realistic noise conditions, surpassing PCA-based approaches in photon-limited imaging.

Findings

DeepFSI outperforms PCA-based FSI in classification accuracy.

DeepFSI shows stronger transfer robustness across photon budgets.

DeepFSI maintains performance under additive Gaussian noise.

Abstract

Modern photon-counting sensors are increasingly dominated by Poisson noise, yet conventional feature-specific imaging (FSI), based on principal component analysis (PCA), is optimized for additive Gaussian noise and variance preservation rather than task-specific objectives, leading to suboptimal performance and a loss of its advantages under Poisson noise. To address this, we introduce DeepFSI, what we believe to be a novel end-to-end optical-electronic framework. DeepFSI "unfreezes" PCA-derived masks, enabling a deep neural network to learn globally optimal measurement masks by computing gradients directly under realistic Poisson and additive noise conditions. Simulations and hardware experiments demonstrate that DeepFSI achieves improved classification accuracy and stronger transfer robustness compared to PCAbased FSI across varying photon budgets, particularly in Poisson-noise-dominant environments. DeepFSI also exhibits enhanced robustness to design choices and performs well under additive Gaussian noise, representing a significant advance for noise-robust computational imaging in photon-limited applications.