Superpixel Cost Volume Excitation for Stereo Matching
| Title: | Superpixel Cost Volume Excitation for Stereo Matching |
|---|---|
| Authors: | Liu, Shanglong, Qi, Lin, Dong, Junyu, Gu, Wenxiang, Xu, Liyi |
| Source: | PRCV 2024 |
| Publication Year: | 2024 |
| Collection: | Computer Science |
| Subject Terms: | Computer Science - Computer Vision and Pattern Recognition |
| More Details: | In this work, we concentrate on exciting the intrinsic local consistency of stereo matching through the incorporation of superpixel soft constraints, with the objective of mitigating inaccuracies at the boundaries of predicted disparity maps. Our approach capitalizes on the observation that neighboring pixels are predisposed to belong to the same object and exhibit closely similar intensities within the probability volume of superpixels. By incorporating this insight, our method encourages the network to generate consistent probability distributions of disparity within each superpixel, aiming to improve the overall accuracy and coherence of predicted disparity maps. Experimental evalua tions on widely-used datasets validate the efficacy of our proposed approach, demonstrating its ability to assist cost volume-based matching networks in restoring competitive performance. Comment: 13 pages, 7 figures |
| Document Type: | Working Paper |
| DOI: | 10.1007/978-981-97-8508-7_2 |
| Access URL: | http://arxiv.org/abs/2411.13105 |
| Accession Number: | edsarx.2411.13105 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2411.13105 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20241120&spage=&pages=&title=Superpixel Cost Volume Excitation for Stereo Matching&atitle=Superpixel%20Cost%20Volume%20Excitation%20for%20Stereo%20Matching&aulast=Liu%2C%20Shanglong&id=DOI:10.1007/978-981-97-8508-7_2 Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2411.13105 RelevancyScore: 1128 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1128.03247070313 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Superpixel Cost Volume Excitation for Stereo Matching – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Liu%2C+Shanglong%22">Liu, Shanglong</searchLink><br /><searchLink fieldCode="AR" term="%22Qi%2C+Lin%22">Qi, Lin</searchLink><br /><searchLink fieldCode="AR" term="%22Dong%2C+Junyu%22">Dong, Junyu</searchLink><br /><searchLink fieldCode="AR" term="%22Gu%2C+Wenxiang%22">Gu, Wenxiang</searchLink><br /><searchLink fieldCode="AR" term="%22Xu%2C+Liyi%22">Xu, Liyi</searchLink> – Name: TitleSource Label: Source Group: Src Data: PRCV 2024 – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subset Label: Collection Group: HoldingsInfo Data: Computer Science – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Computer+Science+-+Computer+Vision+and+Pattern+Recognition%22">Computer Science - Computer Vision and Pattern Recognition</searchLink> – Name: Abstract Label: Description Group: Ab Data: In this work, we concentrate on exciting the intrinsic local consistency of stereo matching through the incorporation of superpixel soft constraints, with the objective of mitigating inaccuracies at the boundaries of predicted disparity maps. Our approach capitalizes on the observation that neighboring pixels are predisposed to belong to the same object and exhibit closely similar intensities within the probability volume of superpixels. By incorporating this insight, our method encourages the network to generate consistent probability distributions of disparity within each superpixel, aiming to improve the overall accuracy and coherence of predicted disparity maps. Experimental evalua tions on widely-used datasets validate the efficacy of our proposed approach, demonstrating its ability to assist cost volume-based matching networks in restoring competitive performance.<br />Comment: 13 pages, 7 figures – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: DOI Label: DOI Group: ID Data: 10.1007/978-981-97-8508-7_2 – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2411.13105" linkWindow="_blank">http://arxiv.org/abs/2411.13105</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2411.13105 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2411.13105 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/978-981-97-8508-7_2 Subjects: – SubjectFull: Computer Science - Computer Vision and Pattern Recognition Type: general Titles: – TitleFull: Superpixel Cost Volume Excitation for Stereo Matching Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Liu, Shanglong – PersonEntity: Name: NameFull: Qi, Lin – PersonEntity: Name: NameFull: Dong, Junyu – PersonEntity: Name: NameFull: Gu, Wenxiang – PersonEntity: Name: NameFull: Xu, Liyi IsPartOfRelationships: – BibEntity: Dates: – D: 20 M: 11 Type: published Y: 2024 |
| ResultId | 1 |