Dense correspondence using multilevel segmentation and affine transformation

Sungil Choi, Kihong Park, Seungryong Kim, Kwanghoon Sohn

Research output: Contribution to journalConference article

Abstract

Establishing dense correspondence fields between images is an important issue with many computer vision and computational photography applications. Although there have been significant advances in estimating dense correspondence fields, it is still difficult to find reliable correspondence fields between a pair of images because of their geometric and photometric variations. In this paper, we propose an unified framework for establishing dense correspondences, consisting of sparse matching, multilevel segmentation, and derivation of affine transformations. Dense correspondence fields are estimated via winner-takes-all (WTA) optimization by utilizing affine transformations, derived from spare matching and multilevel segmentation. The proposed method reduces a size of label search space dramatically, and further extends the dimension of label search space, by leveraging affine transformation with the multilevel segmentation scheme. Our robust dense correspondence estimation is evaluated on extensive experiments, which show that our approach outperforms the state-of-the-art methods both qualitatively and quantitatively.

Original languageEnglish
JournalIS and T International Symposium on Electronic Imaging Science and Technology
DOIs
Publication statusPublished - 2016 Jan 1
EventImage Processing: Machine Vision Applications IX 2016 - San Francisco, United States
Duration: 2016 Feb 142016 Feb 18

Fingerprint

Labels
Photography
Computer vision
photography
computer vision
estimating
derivation
optimization
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Human-Computer Interaction
  • Software
  • Electrical and Electronic Engineering
  • Atomic and Molecular Physics, and Optics

Cite this

@article{f671af8cedbd40d393bf157dd3216e71,
title = "Dense correspondence using multilevel segmentation and affine transformation",
abstract = "Establishing dense correspondence fields between images is an important issue with many computer vision and computational photography applications. Although there have been significant advances in estimating dense correspondence fields, it is still difficult to find reliable correspondence fields between a pair of images because of their geometric and photometric variations. In this paper, we propose an unified framework for establishing dense correspondences, consisting of sparse matching, multilevel segmentation, and derivation of affine transformations. Dense correspondence fields are estimated via winner-takes-all (WTA) optimization by utilizing affine transformations, derived from spare matching and multilevel segmentation. The proposed method reduces a size of label search space dramatically, and further extends the dimension of label search space, by leveraging affine transformation with the multilevel segmentation scheme. Our robust dense correspondence estimation is evaluated on extensive experiments, which show that our approach outperforms the state-of-the-art methods both qualitatively and quantitatively.",
author = "Sungil Choi and Kihong Park and Seungryong Kim and Kwanghoon Sohn",
year = "2016",
month = "1",
day = "1",
doi = "10.2352/ISSN.2470-1173.2016.14.IPMVA-384",
language = "English",
journal = "IS and T International Symposium on Electronic Imaging Science and Technology",
issn = "2470-1173",

}

Dense correspondence using multilevel segmentation and affine transformation. / Choi, Sungil; Park, Kihong; Kim, Seungryong; Sohn, Kwanghoon.

In: IS and T International Symposium on Electronic Imaging Science and Technology, 01.01.2016.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Dense correspondence using multilevel segmentation and affine transformation

AU - Choi, Sungil

AU - Park, Kihong

AU - Kim, Seungryong

AU - Sohn, Kwanghoon

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Establishing dense correspondence fields between images is an important issue with many computer vision and computational photography applications. Although there have been significant advances in estimating dense correspondence fields, it is still difficult to find reliable correspondence fields between a pair of images because of their geometric and photometric variations. In this paper, we propose an unified framework for establishing dense correspondences, consisting of sparse matching, multilevel segmentation, and derivation of affine transformations. Dense correspondence fields are estimated via winner-takes-all (WTA) optimization by utilizing affine transformations, derived from spare matching and multilevel segmentation. The proposed method reduces a size of label search space dramatically, and further extends the dimension of label search space, by leveraging affine transformation with the multilevel segmentation scheme. Our robust dense correspondence estimation is evaluated on extensive experiments, which show that our approach outperforms the state-of-the-art methods both qualitatively and quantitatively.

AB - Establishing dense correspondence fields between images is an important issue with many computer vision and computational photography applications. Although there have been significant advances in estimating dense correspondence fields, it is still difficult to find reliable correspondence fields between a pair of images because of their geometric and photometric variations. In this paper, we propose an unified framework for establishing dense correspondences, consisting of sparse matching, multilevel segmentation, and derivation of affine transformations. Dense correspondence fields are estimated via winner-takes-all (WTA) optimization by utilizing affine transformations, derived from spare matching and multilevel segmentation. The proposed method reduces a size of label search space dramatically, and further extends the dimension of label search space, by leveraging affine transformation with the multilevel segmentation scheme. Our robust dense correspondence estimation is evaluated on extensive experiments, which show that our approach outperforms the state-of-the-art methods both qualitatively and quantitatively.

UR - http://www.scopus.com/inward/record.url?scp=85046056162&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046056162&partnerID=8YFLogxK

U2 - 10.2352/ISSN.2470-1173.2016.14.IPMVA-384

DO - 10.2352/ISSN.2470-1173.2016.14.IPMVA-384

M3 - Conference article

AN - SCOPUS:85046056162

JO - IS and T International Symposium on Electronic Imaging Science and Technology

JF - IS and T International Symposium on Electronic Imaging Science and Technology

SN - 2470-1173

ER -