Depth completion of a single RGB-D image for integral imaging

Shaozhou Zou; Yu Wang

doi:10.1117/12.2639676

19 October 2022 Depth completion of a single RGB-D image for integral imaging

Shaozhou Zou, Yu Wang

Proceedings Volume 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering; 122944F (2022) https://doi.org/10.1117/12.2639676
Event: 7th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE 2022), 2022, Xishuangbanna, China

Abstract

Our laboratory proposes a method for generating elemental images based on fusion of depth images and RGB images for integrated 3D display and has achieved certain results. However, due to the defects of commercial-grade depth cameras, accurate depth estimation of target geometry cannot be accomplished. We propose a deep learning method for estimating accurate depth data of geometry from a single RGB-D image for elemental image generation. Our proposed algorithm uses a deep convolutional network to infer surface normals, object masks and occlusion boundaries from a single RGB-D image as input. Then, based on these refined depth predictions combined with the input original depth image, the depth of all pixels, including the missing pixels in the original input depth image, is solved. Through experiments with various backbones in the proposed deep learning network structure, our resulting model has better completion on deep image inpainting.

Citation Download Citation

Shaozhou Zou and Yu Wang "Depth completion of a single RGB-D image for integral imaging", Proc. SPIE 12294, 7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering, 122944F (19 October 2022); https://doi.org/10.1117/12.2639676

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available