Large-field-of-view lensless imaging with miniaturized sensors

TL;DR

This paper introduces a hierarchical, patch-wise deconvolution approach for lensless imaging that accounts for PSF variation and sensor truncation, enabling high-quality, wide-FOV images with miniaturized sensors.

Contribution

It presents a novel local-to-global hierarchical framework that improves lensless imaging quality and FOV using adaptive local PSF estimation and progressive global integration.

Findings

Achieves superior reconstruction quality over larger FOVs with smaller sensors.

Improves PSNR by 2 dB and SSIM by 5% under extreme miniaturization.

Enhances structural fidelity in lensless imaging results.

Abstract

Lensless cameras replace bulky optics with thin modulation masks, enabling compact imaging systems. However, existing methods rely on an idealized model that assumes a globally shift-invariant point spread function (PSF) and sufficiently large sensors. In reality, the PSF varies spatially across the field of view (FOV), and finite sensor boundaries truncate modulated light--effects that intensify as sensors shrink, degrading peripheral reconstruction quality and limiting the effective FOV. We address these limitations through a local-to-global hierarchical framework grounded in a locally shift-invariant convolution model that explicitly accounts for PSF variation and sensor truncation. Patch-wise learned deconvolution first adaptively estimates local PSFs and reconstructs regions independently. A hierarchical enhancement network then progressively expands its receptive field--from small patches through intermediate blocks to the full image--integrating fine local details with global contextual information. Experiments on public datasets show that our method achieves superior reconstruction quality over a larger effective FOV with significantly reduced sensor sizes. Under extreme miniaturization--sensors reduced to 8% of the original area--we achieve improvements of 2 dB (PSNR) and 5% (SSIM), with particularly notable gains in structural fidelity. Code is available at https://github.com/KB504-public/l2g_lensless_imaging .