Abstract

Lensless cameras are ultra-thin imaging systems that replace the lens with a thin passive optical mask and computation. Passive mask-based lensless cameras encode depth information in their measurements for a certain depth range. Early works have shown that this encoded depth can be used to perform 3D reconstruction of close-range scenes. However, these approaches for 3D reconstructions are typically optimization based and require strong hand-crafted priors and hundreds of iterations to reconstruct. Moreover, the reconstructions suffer from low resolution, noise, and artifacts. In this work, we propose FlatNet3D—a feed-forward deep network that can estimate both depth and intensity from a single lensless capture. FlatNet3D is an end-to-end trainable deep network that directly reconstructs depth and intensity from a lensless measurement using an efficient physics-based 3D mapping stage and a fully convolutional network. Our algorithm is fast and produces high-quality results, which we validate using both simulated and real scenes captured using PhlatCam.

© 2022 Optica Publishing Group

Learned lensless 3D camera

Feng Tian and Weijian Yang
Opt. Express 30(19) 34479-34496 (2022)

Design and single-shot fabrication of lensless cameras with arbitrary point spread functions

Kyung Chul Lee, Junghyun Bae, Nakkyu Baek, Jaewoo Jung, Wook Park, and Seung Ah Lee
Optica 10(1) 72-80 (2023)

DiffuserCam: lensless single-exposure 3D imaging

Nick Antipa, Grace Kuo, Reinhard Heckel, Ben Mildenhall, Emrah Bostan, Ren Ng, and Laura Waller
Optica 5(1) 1-9 (2018)

Extended depth of field for Fresnel zone aperture camera via fast passive depth estimation

Chen Yang, Cong Ni, Xinye Zhang, Yusen Li, Yusheng Zhai, Weiji He, Wenwen Zhang, and Qian Chen
Opt. Express 32(7) 11323-11336 (2024)

Unrolled primal-dual networks for lensless cameras

Oliver Kingshott, Nick Antipa, Emrah Bostan, and Kaan Akşit
Opt. Express 30(26) 46324-46335 (2022)