English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In this study, we present a method for all-around depth estimation frommultiple omnidirectional images for indoor environments. In particular, wefocus on plane-sweeping stereo as the method for depth estimation from theimages. We propose a new icosahedron-based representation and ConvNets foromnidirectional images, which we name "CrownConv" because the representationresembles a crown made of origami. CrownConv can be applied to both fisheyeimages and equirectangular images to extract features. Furthermore, we proposeicosahedron-based spherical sweeping for generating the cost volume on anicosahedron from the extracted features. The cost volume is regularized usingthe three-dimensional CrownConv, and the final depth is obtained by depthregression from the cost volume. Our proposed method is robust to cameraalignments by using the extrinsic camera parameters; therefore, it can achieveprecise depth estimation even when the camera alignment differs from that inthe training dataset. We evaluate the proposed model on synthetic datasets anddemonstrate its effectiveness. As our proposed method is computationallyefficient, the depth is estimated from four fisheye images in less than asecond using a laptop with a GPU. Therefore, it is suitable for real-worldrobotics applications. Our source code is available athttps://github.com/matsuren/crownconv360depth.

360° Depth Estimation from Multiple Fisheye Images with Origami Crown Representation of Icosahedron