DASC

Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence

Seungryong Kim, Dongbo Min, Bumsub Ham, Seungchul Ryu, Minh N. Do, Kwanghoon Sohn

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

38 Citations (Scopus)

Abstract

Establishing dense visual correspondence between multiple images is a fundamental task in many applications of computer vision and computational photography. Classical approaches, which aim to estimate dense stereo and optical flow fields for images adjacent in viewpoint or in time, have been dramatically advanced in recent studies. However, finding reliable visual correspondence in multi-modal or multi-spectral images still remains unsolved. In this paper, we propose a novel dense matching descriptor, called dense adaptive self-correlation (DASC), to effectively address this kind of matching scenarios. Based on the observation that a self-similarity existing within images is less sensitive to modality variations, we define the descriptor with a series of an adaptive self-correlation similarity for patches within a local support window. To further improve the matching quality and runtime efficiency, we propose a randomized receptive field pooling, in which a sampling pattern is optimized with a discriminative learning. Moreover, the computational redundancy that arises when computing densely sampled descriptor over an entire image is dramatically reduced by applying fast edge-aware filtering. Experiments demonstrate the outstanding performance of the DASC descriptor in many cases of multi-modal and multi-spectral correspondence.

Original languageEnglish
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PublisherIEEE Computer Society
Pages2103-2112
Number of pages10
ISBN (Electronic)9781467369640
DOIs
Publication statusPublished - 2015 Oct 14
EventIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States
Duration: 2015 Jun 72015 Jun 12

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume07-12-June-2015
ISSN (Print)1063-6919

Other

OtherIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
CountryUnited States
CityBoston
Period15/6/715/6/12

Fingerprint

Optical flows
Photography
Computer vision
Redundancy
Flow fields
Sampling
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Kim, S., Min, D., Ham, B., Ryu, S., Do, M. N., & Sohn, K. (2015). DASC: Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (pp. 2103-2112). [7298822] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7298822
Kim, Seungryong ; Min, Dongbo ; Ham, Bumsub ; Ryu, Seungchul ; Do, Minh N. ; Sohn, Kwanghoon. / DASC : Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. pp. 2103-2112 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{28f24c2384c34f16bf0fcff3961fbc05,
title = "DASC: Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence",
abstract = "Establishing dense visual correspondence between multiple images is a fundamental task in many applications of computer vision and computational photography. Classical approaches, which aim to estimate dense stereo and optical flow fields for images adjacent in viewpoint or in time, have been dramatically advanced in recent studies. However, finding reliable visual correspondence in multi-modal or multi-spectral images still remains unsolved. In this paper, we propose a novel dense matching descriptor, called dense adaptive self-correlation (DASC), to effectively address this kind of matching scenarios. Based on the observation that a self-similarity existing within images is less sensitive to modality variations, we define the descriptor with a series of an adaptive self-correlation similarity for patches within a local support window. To further improve the matching quality and runtime efficiency, we propose a randomized receptive field pooling, in which a sampling pattern is optimized with a discriminative learning. Moreover, the computational redundancy that arises when computing densely sampled descriptor over an entire image is dramatically reduced by applying fast edge-aware filtering. Experiments demonstrate the outstanding performance of the DASC descriptor in many cases of multi-modal and multi-spectral correspondence.",
author = "Seungryong Kim and Dongbo Min and Bumsub Ham and Seungchul Ryu and Do, {Minh N.} and Kwanghoon Sohn",
year = "2015",
month = "10",
day = "14",
doi = "10.1109/CVPR.2015.7298822",
language = "English",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society",
pages = "2103--2112",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",
address = "United States",

}

Kim, S, Min, D, Ham, B, Ryu, S, Do, MN & Sohn, K 2015, DASC: Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015., 7298822, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE Computer Society, pp. 2103-2112, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 15/6/7. https://doi.org/10.1109/CVPR.2015.7298822

DASC : Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence. / Kim, Seungryong; Min, Dongbo; Ham, Bumsub; Ryu, Seungchul; Do, Minh N.; Sohn, Kwanghoon.

IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society, 2015. p. 2103-2112 7298822 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

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

TY - GEN

T1 - DASC

T2 - Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence

AU - Kim, Seungryong

AU - Min, Dongbo

AU - Ham, Bumsub

AU - Ryu, Seungchul

AU - Do, Minh N.

AU - Sohn, Kwanghoon

PY - 2015/10/14

Y1 - 2015/10/14

N2 - Establishing dense visual correspondence between multiple images is a fundamental task in many applications of computer vision and computational photography. Classical approaches, which aim to estimate dense stereo and optical flow fields for images adjacent in viewpoint or in time, have been dramatically advanced in recent studies. However, finding reliable visual correspondence in multi-modal or multi-spectral images still remains unsolved. In this paper, we propose a novel dense matching descriptor, called dense adaptive self-correlation (DASC), to effectively address this kind of matching scenarios. Based on the observation that a self-similarity existing within images is less sensitive to modality variations, we define the descriptor with a series of an adaptive self-correlation similarity for patches within a local support window. To further improve the matching quality and runtime efficiency, we propose a randomized receptive field pooling, in which a sampling pattern is optimized with a discriminative learning. Moreover, the computational redundancy that arises when computing densely sampled descriptor over an entire image is dramatically reduced by applying fast edge-aware filtering. Experiments demonstrate the outstanding performance of the DASC descriptor in many cases of multi-modal and multi-spectral correspondence.

AB - Establishing dense visual correspondence between multiple images is a fundamental task in many applications of computer vision and computational photography. Classical approaches, which aim to estimate dense stereo and optical flow fields for images adjacent in viewpoint or in time, have been dramatically advanced in recent studies. However, finding reliable visual correspondence in multi-modal or multi-spectral images still remains unsolved. In this paper, we propose a novel dense matching descriptor, called dense adaptive self-correlation (DASC), to effectively address this kind of matching scenarios. Based on the observation that a self-similarity existing within images is less sensitive to modality variations, we define the descriptor with a series of an adaptive self-correlation similarity for patches within a local support window. To further improve the matching quality and runtime efficiency, we propose a randomized receptive field pooling, in which a sampling pattern is optimized with a discriminative learning. Moreover, the computational redundancy that arises when computing densely sampled descriptor over an entire image is dramatically reduced by applying fast edge-aware filtering. Experiments demonstrate the outstanding performance of the DASC descriptor in many cases of multi-modal and multi-spectral correspondence.

UR - http://www.scopus.com/inward/record.url?scp=84959241558&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959241558&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7298822

DO - 10.1109/CVPR.2015.7298822

M3 - Conference contribution

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

SP - 2103

EP - 2112

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

ER -

Kim S, Min D, Ham B, Ryu S, Do MN, Sohn K. DASC: Dense adaptive self-correlation descriptor for multi-modal and multi-spectral correspondence. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. IEEE Computer Society. 2015. p. 2103-2112. 7298822. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2015.7298822