View : 73 Download: 0

Discrete-Continuous Transformation Matching for Dense Semantic Correspondence

Title
Discrete-Continuous Transformation Matching for Dense Semantic Correspondence
Authors
Kim, SeungryongMin, DongboLin, StephenSohn, Kwanghoon
Ewha Authors
민동보
Issue Date
2020
Journal Title
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN
0162-8828JCR Link

1939-3539JCR Link
Citation
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE vol. 42, no. 1, pp. 59 - 73
Keywords
SemanticsOptimizationStrainComputational modelingOptical imagingLabelingConvolutionDense semantic correspondencediscrete optimizationcontinuous optimizationinterative inference
Publisher
IEEE COMPUTER SOC
Indexed
SCI; SCIE; SCOPUS WOS scopus
Document Type
Article
Abstract
Techniques for dense semantic correspondence have provided limited ability to deal with the geometric variations that commonly exist between semantically similar images. While variations due to scale and rotation have been examined, there is a lack of practical solutions for more complex deformations such as affine transformations because of the tremendous size of the associated solution space. To address this problem, we present a discrete-continuous transformation matching (DCTM) framework where dense affine transformation fields are inferred through a discrete label optimization in which the labels are iteratively updated via continuous regularization. In this way, our approach draws solutions from the continuous space of affine transformations in a manner that can be computed efficiently through constant-time edge-aware filtering and a proposed affine-varying CNN-based descriptor. Furthermore, leveraging correspondence consistency and confidence-guided filtering in each iteration facilitates the convergence of our method. Experimental results show that this model outperforms the state-of-the-art methods for dense semantic correspondence on various benchmarks and applications.
DOI
10.1109/TPAMI.2018.2878240
Appears in Collections:
엘텍공과대학 > 컴퓨터공학과 > Journal papers
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE