EdgeConv with Attention Module for Monocular Depth Estimation

Minhyeok Lee, Sangwon Hwang, Chaewon Park, Sangyoun Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Monocular depth estimation is an especially important task in robotics and autonomous driving, where 3D structural information is essential. However, extreme lighting conditions and complex surface objects make it difficult to predict depth in a single image. Therefore, to generate accurate depth maps, it is important for the model to learn structural information about the scene. We propose a novel Patch-Wise EdgeConv Module (PEM) and EdgeConv Attention Module (EAM) to solve the difficulty of monocular depth estimation. The proposed modules extract structural information by learning the relationship between image patches close to each other in space using edge convolution. Our method is evaluated on two popular datasets, the NYU Depth V2 and the KITTI Eigen split, achieving state-of-the-art performance. We prove that the proposed model predicts depth robustly in challenging scenes through various comparative experiments.

Original languageEnglish
Title of host publicationProceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2364-2373
Number of pages10
ISBN (Electronic)9781665409155
DOIs
Publication statusPublished - 2022
Event22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022 - Waikoloa, United States
Duration: 2022 Jan 42022 Jan 8

Publication series

NameProceedings - 2022 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022

Conference

Conference22nd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2022
Country/TerritoryUnited States
CityWaikoloa
Period22/1/422/1/8

Bibliographical note

Funding Information:
Acknowledgement. This work was supported by the Institute of Information & communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT) (No. 2021-0-00172, The development of human Re-identification and masked face recognition based on CCTV camera)

Publisher Copyright:
© 2022 IEEE.

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'EdgeConv with Attention Module for Monocular Depth Estimation'. Together they form a unique fingerprint.

Cite this