360$^\circ$ Depth Estimation from Multiple Fisheye Images with Origami Crown Representation of Icosahedron

TL;DR

This paper introduces CrownConv, a novel icosahedron-based neural network architecture for fast and accurate all-around depth estimation from multiple fisheye and omnidirectional images, suitable for robotics.

Contribution

The paper proposes a new icosahedron-based CrownConv representation and spherical sweeping method for omnidirectional depth estimation, improving robustness and computational efficiency.

Findings

Effective depth estimation from four fisheye images in under a second

Robust to camera alignment variations

Validated on synthetic datasets

Abstract

In this study, we present a method for all-around depth estimation from multiple omnidirectional images for indoor environments. In particular, we focus on plane-sweeping stereo as the method for depth estimation from the images. We propose a new icosahedron-based representation and ConvNets for omnidirectional images, which we name "CrownConv" because the representation resembles a crown made of origami. CrownConv can be applied to both fisheye images and equirectangular images to extract features. Furthermore, we propose icosahedron-based spherical sweeping for generating the cost volume on an icosahedron from the extracted features. The cost volume is regularized using the three-dimensional CrownConv, and the final depth is obtained by depth regression from the cost volume. Our proposed method is robust to camera alignments by using the extrinsic camera parameters; therefore, it can achieve precise depth estimation even when the camera alignment differs from that in the training dataset. We evaluate the proposed model on synthetic datasets and demonstrate its effectiveness. As our proposed method is computationally efficient, the depth is estimated from four fisheye images in less than a second using a laptop with a GPU. Therefore, it is suitable for real-world robotics applications. Our source code is available at https://github.com/matsuren/crownconv360depth.