Self-supervised depth completion with attention-based loss

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

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

1 Citation (Scopus)


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.

Original languageEnglish
Title of host publicationInternational Workshop on Advanced Imaging Technology, IWAIT 2020
EditorsPhooi Yee Lau, Mohammad Shobri
ISBN (Electronic)9781510638358
Publication statusPublished - Jun 2020
EventInternational Workshop on Advanced Imaging Technology, IWAIT 2020 - Yogyakarta, Indonesia
Duration: 5 Jan 20207 Jan 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


ConferenceInternational Workshop on Advanced Imaging Technology, IWAIT 2020


  • Attention-based loss
  • Deep completion
  • Monocular depth estimation
  • Self-supervised
  • Statistical properties

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering


Dive into the research topics of 'Self-supervised depth completion with attention-based loss'. Together they form a unique fingerprint.

Cite this