基于学习衍射光学的单次超光谱深度成像
Single-shot Hyperspectral-Depth Imaging with Learned Diffractive Optics
摘要：
几十年来，成像深度和光谱一直被广泛研究。最近，超光谱深度（HS-D）成像出现，通过结合两个不同的成像系统，一个用于深度，另一个用于光谱，同时捕获这两种信息。虽然是准确的，但这种组合方法会导致增加的形状因子、成本、捕获时间和对准/配准问题。在这项工作中，从组合原理出发，我们提出了一个紧凑的单次拍摄单目HS-D成像方法。我们的方法使用衍射光学元件（DOE），其点扩散函数的变化相对于深度和光谱。这使我们能够从单个捕获的图像中重建光谱和深度。为此，我们开发了一个微分模拟器和基于神经网络的重建，通过自动微分联合优化。为了便于学习DOE，我们通过构建获取高质量地面真实的台式HS-D成像仪来呈现第一个HS-D数据集。我们评估我们的方法与合成和真实的实验，通过建立一个实验原型，并实现国家的最先进的HS-D成像结果。
英文摘要：
Imaging depth and spectrum have been extensively studied in isolation from each other for decades. Recently, hyperspectral-depth (HS-D) imaging emerges to capture both information simultaneously by combining two different imaging systems; one for depth, the other for spectrum. While being accurate, this combinational approach induces increased form factor, cost, capture time, and alignment/registration problems. In this work, departing from the combinational principle, we propose a compact single-shot monocular HS-D imaging method. Our method uses a diffractive optical element (DOE), the point spread function of which changes with respect to both depth and spectrum. This enables us to reconstruct spectrum and depth from a single captured image. To this end, we develop a differentiable simulator and a neural-network-based reconstruction that are jointly optimized via automatic differentiation. To facilitate learning the DOE, we present a first HS-D dataset by building a benchtop HS-D imager that acquires high-quality ground truth. We evaluate our method with synthetic and real experiments by building an experimental prototype and achieve state-of-the-art HS-D imaging results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
