Single-Image Depth Estimation Based on Fourier Domain Analysis

Jae Han Lee, Minhyeok Heo, Kyung Rae Kim, Chang-Su Kim

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

19 Citations (Scopus)

Abstract

We propose a deep learning algorithm for single-image depth estimation based on the Fourier frequency domain analysis. First, we develop a convolutional neural network structure and propose a new loss function, called depth-balanced Euclidean loss, to train the network reliably for a wide range of depths. Then, we generate multiple depth map candidates by cropping input images with various cropping ratios. In general, a cropped image with a small ratio yields depth details more faithfully, while that with a large ratio provides the overall depth distribution more reliably. To take advantage of these complementary properties, we combine the multiple candidates in the frequency domain. Experimental results demonstrate that proposed algorithm provides the state-of-art performance. Furthermore, through the frequency domain analysis, we validate the efficacy of the proposed algorithm in most frequency bands.

Original languageEnglish
Title of host publicationProceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PublisherIEEE Computer Society
Pages330-339
Number of pages10
ISBN (Electronic)9781538664209
DOIs
Publication statusPublished - 2018 Dec 14
Event31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 - Salt Lake City, United States
Duration: 2018 Jun 182018 Jun 22

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
CountryUnited States
CitySalt Lake City
Period18/6/1818/6/22

Fingerprint

Frequency domain analysis
Learning algorithms
Frequency bands
Neural networks
Deep learning

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Lee, J. H., Heo, M., Kim, K. R., & Kim, C-S. (2018). Single-Image Depth Estimation Based on Fourier Domain Analysis. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018 (pp. 330-339). [8578140] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society. https://doi.org/10.1109/CVPR.2018.00042

Single-Image Depth Estimation Based on Fourier Domain Analysis. / Lee, Jae Han; Heo, Minhyeok; Kim, Kyung Rae; Kim, Chang-Su.

Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society, 2018. p. 330-339 8578140 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

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

Lee, JH, Heo, M, Kim, KR & Kim, C-S 2018, Single-Image Depth Estimation Based on Fourier Domain Analysis. in Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018., 8578140, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, pp. 330-339, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, United States, 18/6/18. https://doi.org/10.1109/CVPR.2018.00042
Lee JH, Heo M, Kim KR, Kim C-S. Single-Image Depth Estimation Based on Fourier Domain Analysis. In Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society. 2018. p. 330-339. 8578140. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2018.00042
Lee, Jae Han ; Heo, Minhyeok ; Kim, Kyung Rae ; Kim, Chang-Su. / Single-Image Depth Estimation Based on Fourier Domain Analysis. Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018. IEEE Computer Society, 2018. pp. 330-339 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{d4a64ce2cb9c486485034486836ae760,
title = "Single-Image Depth Estimation Based on Fourier Domain Analysis",
abstract = "We propose a deep learning algorithm for single-image depth estimation based on the Fourier frequency domain analysis. First, we develop a convolutional neural network structure and propose a new loss function, called depth-balanced Euclidean loss, to train the network reliably for a wide range of depths. Then, we generate multiple depth map candidates by cropping input images with various cropping ratios. In general, a cropped image with a small ratio yields depth details more faithfully, while that with a large ratio provides the overall depth distribution more reliably. To take advantage of these complementary properties, we combine the multiple candidates in the frequency domain. Experimental results demonstrate that proposed algorithm provides the state-of-art performance. Furthermore, through the frequency domain analysis, we validate the efficacy of the proposed algorithm in most frequency bands.",
author = "Lee, {Jae Han} and Minhyeok Heo and Kim, {Kyung Rae} and Chang-Su Kim",
year = "2018",
month = "12",
day = "14",
doi = "10.1109/CVPR.2018.00042",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "330--339",
booktitle = "Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018",

}

TY - GEN

T1 - Single-Image Depth Estimation Based on Fourier Domain Analysis

AU - Lee, Jae Han

AU - Heo, Minhyeok

AU - Kim, Kyung Rae

AU - Kim, Chang-Su

PY - 2018/12/14

Y1 - 2018/12/14

N2 - We propose a deep learning algorithm for single-image depth estimation based on the Fourier frequency domain analysis. First, we develop a convolutional neural network structure and propose a new loss function, called depth-balanced Euclidean loss, to train the network reliably for a wide range of depths. Then, we generate multiple depth map candidates by cropping input images with various cropping ratios. In general, a cropped image with a small ratio yields depth details more faithfully, while that with a large ratio provides the overall depth distribution more reliably. To take advantage of these complementary properties, we combine the multiple candidates in the frequency domain. Experimental results demonstrate that proposed algorithm provides the state-of-art performance. Furthermore, through the frequency domain analysis, we validate the efficacy of the proposed algorithm in most frequency bands.

AB - We propose a deep learning algorithm for single-image depth estimation based on the Fourier frequency domain analysis. First, we develop a convolutional neural network structure and propose a new loss function, called depth-balanced Euclidean loss, to train the network reliably for a wide range of depths. Then, we generate multiple depth map candidates by cropping input images with various cropping ratios. In general, a cropped image with a small ratio yields depth details more faithfully, while that with a large ratio provides the overall depth distribution more reliably. To take advantage of these complementary properties, we combine the multiple candidates in the frequency domain. Experimental results demonstrate that proposed algorithm provides the state-of-art performance. Furthermore, through the frequency domain analysis, we validate the efficacy of the proposed algorithm in most frequency bands.

UR - http://www.scopus.com/inward/record.url?scp=85055442364&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055442364&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2018.00042

DO - 10.1109/CVPR.2018.00042

M3 - Conference contribution

AN - SCOPUS:85055442364

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 330

EP - 339

BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018

PB - IEEE Computer Society

ER -