Self-supervised depth completion with attention-based loss

Yingyu Wang; Yakun Ju; Muwei Jian; Kin-Man Lam; Lin Qia; Junyu Dong

doi:10.1117/12.2566222

1 June 2020 Self-supervised depth completion with attention-based loss

Yingyu Wang, Yakun Ju, Muwei Jian, Kin-Man Lam, Lin Qia, Junyu Dong

Proceedings Volume 11515, International Workshop on Advanced Imaging Technology (IWAIT) 2020; 115152T (2020) https://doi.org/10.1117/12.2566222
Event: International Workshop on Advanced Imaging Technologies 2020 (IWAIT 2020), 2020, Yogyakarta, Indonesia

Abstract

Deep completion which predicts dense depth from sparse depth has important applications in the fields of robotics, autonomous driving and virtual reality. It compensates for the shortcomings of low accuracy in monocular depth estimation. However, the previous deep completion works evenly processed each depth pixel and ignored the statistical properties of the depth value distribution. In this paper, we propose a self-supervised framework that can generate accurate dense depth from RGB images and sparse depth without the need for dense depth labels. We propose a novel attention-based loss that takes into account the statistical properties of the depth value distribution. We evaluate our approach on the KITTI Dataset. The experimental results show that our method achieves state-of-the-art performance. At the same time, ablation study proves that our method can effectively improve the accuracy of the results.

Citation Download Citation

Yingyu Wang, Yakun Ju, Muwei Jian, Kin-Man Lam, Lin Qia, and Junyu Dong "Self-supervised depth completion with attention-based loss", Proc. SPIE 11515, International Workshop on Advanced Imaging Technology (IWAIT) 2020, 115152T (1 June 2020); https://doi.org/10.1117/12.2566222

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

RGB color model

Signal attenuation

Cameras

Data acquisition

Computer programming

Convolution

Image fusion

Show All Keywords

Keywords/Phrases

Search In:

Publication Years