Abstract
Recently, computational lensless imaging had been making progress with the evolution of artificial neural networks. Nonetheless, generative models for image reconstruction inherit challenge due to its ill-posed nature. We proposed a deep neural network based lensless imaging system by optimizing perceptual loss exclusively to end-to-end reconstruct images conforming human preference.
Original language | English |
---|---|
Pages (from-to) | 1153-1156 |
Number of pages | 4 |
Journal | Proceedings of the International Display Workshops |
Volume | 29 |
DOIs | |
State | Published - 2022 |
Event | 29th International Display Workshops, IDW 2022 - Fukuoka, Japan Duration: 14 Dec 2022 → 16 Dec 2022 |
Keywords
- Lensless imaging
- artificial neural network
- coded aperture
- perceptual loss