摘要
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.
原文 | English |
---|---|
頁(從 - 到) | 1153-1156 |
頁數 | 4 |
期刊 | Proceedings of the International Display Workshops |
卷 | 29 |
DOIs | |
出版狀態 | Published - 2022 |
事件 | 29th International Display Workshops, IDW 2022 - Fukuoka, 日本 持續時間: 14 12月 2022 → 16 12月 2022 |