Revisiting single image depth estimation: Toward higher resolution maps with accurate object boundaries

Junjie Hu, Mete Ozay, Yan Zhang, Takayuki Okatani

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

20 Citations (Scopus)

Abstract

This paper considers the problem of single image depth estimation. The employment of convolutional neural networks (CNNs) has recently brought about significant advancements in the research of this problem. However, most existing methods suffer from loss of spatial resolution in the estimated depth maps; a typical symptom is distorted and blurry reconstruction of object boundaries. In this paper, toward more accurate estimation with a focus on depth maps with higher spatial resolution, we propose two improvements to existing approaches. One is about the strategy of fusing features extracted at different scales, for which we propose an improved network architecture consisting of four modules: an encoder, decoder, multi-scale feature fusion module, and refinement module. The other is about loss functions for measuring inference errors used in training. We show that three loss terms, which measure errors in depth, gradients and surface normals, respectively, contribute to improvement of accuracy in an complementary fashion. Experimental results show that these two improvements enable to attain higher accuracy than the current state-of-the-arts, which is given by finer resolution reconstruction, for example, with small objects and object boundaries.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1043-1051
Number of pages9
ISBN (Electronic)9781728119755
DOIs
Publication statusPublished - 2019 Mar 4
Event19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019 - Waikoloa Village, United States
Duration: 2019 Jan 72019 Jan 11

Publication series

NameProceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019

Conference

Conference19th IEEE Winter Conference on Applications of Computer Vision, WACV 2019
CountryUnited States
CityWaikoloa Village
Period19/1/719/1/11

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Revisiting single image depth estimation: Toward higher resolution maps with accurate object boundaries'. Together they form a unique fingerprint.

  • Cite this

    Hu, J., Ozay, M., Zhang, Y., & Okatani, T. (2019). Revisiting single image depth estimation: Toward higher resolution maps with accurate object boundaries. In Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019 (pp. 1043-1051). [8658954] (Proceedings - 2019 IEEE Winter Conference on Applications of Computer Vision, WACV 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WACV.2019.00116