End-to-end snapshot compressed super-resolution imaging with deep optics

• DOI: 10.1364/optica.450657
• Publication Date: 2022-03-15T12:00:26Z
• Authors: Bo Zhang; Xin Yuan; Chao Deng; Zhihong Zhang; Jinli Suo; Qionghai Dai
• Keywords: Snapshot (computer storage)

Capturing both fine structure and high dynamics of the scene is demanded in many applications. However, such throughput recording requires significant transmission bandwidth large storage. Off-the-shelf super-resolution temporal compressive sensing can partially address this challenge, but directly concatenating two techniques fails to boost because artifact accumulation magnification sequential reconstruction. In Letter, we propose an encoded capturing approach simultaneously increase spatial resolvability with a low-bandwidth camera sensor. Specifically, introduce point-spread-function (PSF) engineering via deep optics encode details fast motions into low-resolution snapshot. Furthermore, develop end-to-end neural network optimize PSF retrieve high-throughput videos from compactly compressed measurement. Trained on simulation data fine-tuned fit system settings, our offers <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> <mml:mn>128</mml:mn> <mml:mo>×</mml:mo> </mml:math> compared conventional imaging.