Single-shot Hyperspectral-Depth Imaging with Learned Diffractive Optics

TL;DR

This paper introduces a compact, single-shot hyperspectral-depth imaging method using learned diffractive optics, enabling simultaneous spectrum and depth capture with high accuracy from a single image.

Contribution

It proposes a novel monocular HS-D imaging approach with a learnable diffractive optical element and a joint neural network reconstruction, reducing complexity and improving performance.

Findings

Achieved state-of-the-art HS-D imaging results

Developed a differentiable simulator for joint optimization

Built a new HS-D dataset with ground truth

Abstract

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.