A generative approach for lensless imaging in low-light conditions

TL;DR

This paper introduces a novel combined model-driven and data-driven reconstruction method for lensless imaging in low-light conditions, significantly improving image quality despite complex noise interference.

Contribution

It presents a new robust reconstruction framework that integrates physics-based guidance with generative models, enhancing image clarity in low-light lensless imaging.

Findings

Substantial visual quality improvements demonstrated in simulations.

Effective noise suppression in low-light lensless imaging environments.

Stable and fast image generation using modified diffusion modules.

Abstract

Lensless imaging offers a lightweight, compact alternative to traditional lens-based systems, ideal for exploration in space-constrained environments. However, the absence of a focusing lens and limited lighting in such environments often result in low-light conditions, where the measurements suffer from complex noise interference due to insufficient capture of photons. This study presents a robust reconstruction method for high-quality imaging in low-light scenarios, employing two complementary perspectives: model-driven and data-driven. First, we apply a physic-model-driven perspective to reconstruct in the range space of the pseudo-inverse of the measurement model as a first guidance to extract information in the noisy measurements. Then, we integrate a generative-model based perspective to suppress residual noises as the second guidance to suppress noises in the initial noisy results. Specifically, a learnable Wiener filter-based module generates an initial noisy reconstruction. Then, for fast and, more importantly, stable generation of the clear image from the noisy version, we implement a modified conditional generative diffusion module. This module converts the raw image into the latent wavelet domain for efficiency and uses modified bidirectional training processes for stabilization. Simulations and real-world experiments demonstrate substantial improvements in overall visual quality, advancing lensless imaging in challenging low-light environments.