SPDepth: Enhancing Self-Supervised Indoor Monocular Depth Estimation via Self-Propagation

Xiaotong Guo, Huijie Zhao (), Shuwei Shao, Xudong Li, Baochang Zhang and Na Li
Additional contact information
Xiaotong Guo: School of Instrumentation and Optoelectronic Engineering, Key Laboratory of Precision Opto-Mechatronics Technology, Ministry of Education, Beihang University, Beijing 100191, China
Huijie Zhao: School of Artificial Intelligence, Beihang University, Beijing 100191, China
Shuwei Shao: School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China
Xudong Li: School of Instrumentation and Optoelectronic Engineering, Key Laboratory of Precision Opto-Mechatronics Technology, Ministry of Education, Beihang University, Beijing 100191, China
Baochang Zhang: School of Artificial Intelligence, Beihang University, Beijing 100191, China
Na Li: School of Artificial Intelligence, Beihang University, Beijing 100191, China

Future Internet, 2024, vol. 16, issue 10, 1-14

Abstract: Due to the existence of low-textured areas in indoor scenes, some self-supervised depth estimation methods have specifically designed sparse photometric consistency losses and geometry-based losses. However, some of the loss terms cannot supervise all the pixels, which limits the performance of these methods. Some approaches introduce an additional optical flow network to provide dense correspondences supervision, but overload the loss function. In this paper, we propose to perform depth self-propagation based on feature self-similarities, where high-accuracy depths are propagated from supervised pixels to unsupervised ones. The enhanced self-supervised indoor monocular depth estimation network is called SPDepth. Since depth self-similarities are significant in a local range, a local window self-attention module is embedded at the end of the network to propagate depths in a window. The depth of a pixel is weighted using the feature correlation scores with other pixels in the same window. The effectiveness of self-propagation mechanism is demonstrated in the experiments on the NYU Depth V2 dataset. The root-mean-squared error of SPDepth is 0.585 and the δ 1 accuracy is 77.6%. Zero-shot generalization studies are also conducted on the 7-Scenes dataset and provide a more comprehensive analysis about the application characteristics of SPDepth.

Keywords: self-supervised learning; indoor monocular depth estimation; self-propagation (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/16/10/375/pdf (application/pdf)
https://www.mdpi.com/1999-5903/16/10/375/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:16:y:2024:i:10:p:375-:d:1500088

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().