https://doi.org/10.1051/epjconf/202226604005
Single-shot 3D endoscopic imaging exploiting a diffuser and neural networks
1 Laboratory of Measurement and Sensor Systems, TU Dresden, 01062 Dresden, Germany
2 Competence Center for Biomedical Computational Laser Systems (BIOLAS), TU Dresden, Germany
* e-mail: julian.lich@tu-dresden.de
Published online: 13 October 2022
Lens-based endoscopes offer high lateral resolution, but suffer from rigid imaging properties, such as a fixed focal plane. We present a miniaturized 0.5 mm diameter endoscope in which the objective lens is replaced by an optical diffuser. The intensity information of the object space is scattered and passed to a camera via a coherent fibre bundle. The image is reconstructed by a neural network. The field of view and resolution depend on the object distance. 3D-single-shot imaging up to video rate can be enabled. The approach shows great potential for applications like robust 3D fluorescence imaging.
© The Authors, published by EDP Sciences
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
