Abstract
We train space-time neural representations in an unsupervised, physics-based pipeline to reconstruct videos from DiffuserCam lensless imagers. Our method takes advantage of redundant information between frames, demonstrating improved quality when compared to frame-by-frame approaches.
© 2022 The Author(s)
PDF Article | Presentation VideoMore Like This
Clare Lin, Fanglin Linda Liu, and Laura Waller
MW4A.3 Microscopy Histopathology and Analytics (Microscopy) 2022
Honghao Huang, Chengyang Hu, Sigang Yang, Minghua Chen, and Hongwei Chen
JW3B.172 CLEO: Applications and Technology (CLEO:A&T) 2022
Manuel Herrera-Poveda, David Morales-Norato, Hans Garcia, Sergio Castillo, Andrés Jerez, and Henry Arguello
CTh2A.3 Computational Optical Sensing and Imaging (COSI) 2023