Deep stereo confidence prediction for depth estimation

Sunok Kim, Dongbo Min, Bumsub Ham, Seungryong Kim, Kwanghoon Sohn

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

1 Citation (Scopus)

Abstract

We present a novel method that predicts a confidence to improve the accuracy of an estimated depth map in stereo matching. In contrast to existing learning based approaches relying on hand-crafted confidence features, we cast this problem into a convolutional neural network, learned using both a matching cost volume and its associated disparity map. As the size of the matching cost volume varies depending on a search range of stereo image pairs, we propose to use a top-K matching probability volume layer so that an input size for convolutional layers remains unchanged. Experimental results demonstrate that the proposed method outperforms the state-of-the-art confidence estimation approaches on various benchmarks.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages992-996
Number of pages5
ISBN (Electronic)9781509021758
DOIs
Publication statusPublished - 2018 Feb 20
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: 2017 Sep 172017 Sep 20

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2017-September
ISSN (Print)1522-4880

Other

Other24th IEEE International Conference on Image Processing, ICIP 2017
CountryChina
CityBeijing
Period17/9/1717/9/20

Fingerprint

Costs
Neural networks

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Kim, S., Min, D., Ham, B., Kim, S., & Sohn, K. (2018). Deep stereo confidence prediction for depth estimation. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings (pp. 992-996). (Proceedings - International Conference on Image Processing, ICIP; Vol. 2017-September). IEEE Computer Society. https://doi.org/10.1109/ICIP.2017.8296430
Kim, Sunok ; Min, Dongbo ; Ham, Bumsub ; Kim, Seungryong ; Sohn, Kwanghoon. / Deep stereo confidence prediction for depth estimation. 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. IEEE Computer Society, 2018. pp. 992-996 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{c80d6f855d5c49df851c37b6d4fe19d5,
title = "Deep stereo confidence prediction for depth estimation",
abstract = "We present a novel method that predicts a confidence to improve the accuracy of an estimated depth map in stereo matching. In contrast to existing learning based approaches relying on hand-crafted confidence features, we cast this problem into a convolutional neural network, learned using both a matching cost volume and its associated disparity map. As the size of the matching cost volume varies depending on a search range of stereo image pairs, we propose to use a top-K matching probability volume layer so that an input size for convolutional layers remains unchanged. Experimental results demonstrate that the proposed method outperforms the state-of-the-art confidence estimation approaches on various benchmarks.",
author = "Sunok Kim and Dongbo Min and Bumsub Ham and Seungryong Kim and Kwanghoon Sohn",
year = "2018",
month = "2",
day = "20",
doi = "10.1109/ICIP.2017.8296430",
language = "English",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "992--996",
booktitle = "2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings",
address = "United States",

}

Kim, S, Min, D, Ham, B, Kim, S & Sohn, K 2018, Deep stereo confidence prediction for depth estimation. in 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. Proceedings - International Conference on Image Processing, ICIP, vol. 2017-September, IEEE Computer Society, pp. 992-996, 24th IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, 17/9/17. https://doi.org/10.1109/ICIP.2017.8296430

Deep stereo confidence prediction for depth estimation. / Kim, Sunok; Min, Dongbo; Ham, Bumsub; Kim, Seungryong; Sohn, Kwanghoon.

2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. IEEE Computer Society, 2018. p. 992-996 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2017-September).

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

TY - GEN

T1 - Deep stereo confidence prediction for depth estimation

AU - Kim, Sunok

AU - Min, Dongbo

AU - Ham, Bumsub

AU - Kim, Seungryong

AU - Sohn, Kwanghoon

PY - 2018/2/20

Y1 - 2018/2/20

N2 - We present a novel method that predicts a confidence to improve the accuracy of an estimated depth map in stereo matching. In contrast to existing learning based approaches relying on hand-crafted confidence features, we cast this problem into a convolutional neural network, learned using both a matching cost volume and its associated disparity map. As the size of the matching cost volume varies depending on a search range of stereo image pairs, we propose to use a top-K matching probability volume layer so that an input size for convolutional layers remains unchanged. Experimental results demonstrate that the proposed method outperforms the state-of-the-art confidence estimation approaches on various benchmarks.

AB - We present a novel method that predicts a confidence to improve the accuracy of an estimated depth map in stereo matching. In contrast to existing learning based approaches relying on hand-crafted confidence features, we cast this problem into a convolutional neural network, learned using both a matching cost volume and its associated disparity map. As the size of the matching cost volume varies depending on a search range of stereo image pairs, we propose to use a top-K matching probability volume layer so that an input size for convolutional layers remains unchanged. Experimental results demonstrate that the proposed method outperforms the state-of-the-art confidence estimation approaches on various benchmarks.

UR - http://www.scopus.com/inward/record.url?scp=85045311133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045311133&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2017.8296430

DO - 10.1109/ICIP.2017.8296430

M3 - Conference contribution

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 992

EP - 996

BT - 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings

PB - IEEE Computer Society

ER -

Kim S, Min D, Ham B, Kim S, Sohn K. Deep stereo confidence prediction for depth estimation. In 2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings. IEEE Computer Society. 2018. p. 992-996. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2017.8296430