FlatNet3D: intensity and absolute depth from single-shot lensless capture
FlatNet3D: intensity and absolute depth from single-shot lensless capture
复制标题
DOI：
10.1364/josaa.466286
复制
发表时间：
2022-10-01
影响因子：
1.9
通讯作者：
Mitra, Kaushik
中科院分区：
文献类型：
--
作者：
Bagadthey, Dhruvjyoti;Prabhu, Sanjana;Mitra, Kaushik
无镜头相机是超薄成像系统，用薄的无源光学掩模和计算取代了镜头。无源掩模无透镜相机在测量某一深度范围时对深度信息进行编码。早期的研究表明，这种编码深度可以用于近距离场景的3D重建。然而，这些3D重建方法通常是基于优化的，需要强大的手工制作先验和数百次迭代来重建。此外，重建还存在分辨率低、噪声和伪影等问题。在这项工作中，我们提出了flatnet3d -一种前馈深度网络，可以从单次无透镜捕获中估计深度和强度。FlatNet3D是一个端到端可训练的深度网络，使用高效的基于物理的3D映射阶段和全卷积网络，直接从无透镜测量中重建深度和强度。我们的算法速度快，产生高质量的结果，我们使用使用PhlatCam捕获的模拟和真实场景进行验证。(c) 2022光学出版集团
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. (c) 2022 Optica Publishing Group