EGO-VC – Evolutionary GPU-Optimization of Visual Correspondences for Image Alignment

dc.contributor.authorChang, Thomas Vincent
dc.contributor.authorHartmann, Kay
dc.contributor.authorKuth, Bastian
dc.contributor.authorSeibt, Simon
dc.contributor.authorvon Rymon Lipinski, Bartosz
dc.contributor.editorSkala, Václav
dc.date.accessioned2025-07-30T09:15:16Z
dc.date.available2025-07-30T09:15:16Z
dc.date.issued2025
dc.description.abstract-translatedMany computer vision applications, such as panoramic stitching, image morphing, and image registration depend on precise feature correspondences. While current machine-learning-based methods excel at detecting precise feature matches, they do not necessarily guarantee visual alignment. This work presents an evolutionary, mesh-based optimization framework that enhances alignment quality and improves visual coherence as a postprocessing step for any feature-matching algorithm: The approach employs the well-known enhanced correlation coefficient (ECC) as a visual error metric, efficiently computed in parallel using the rasterization capabilities of modern graphics hardware. Given any state-of-the-art feature matcher, the proposed method constructs a Delaunay feature point mesh and evolutionarily refines the ECC alignment of each generated triangle. This results in a more precise registration beyond the accuracy of initial feature matches. Extensive evaluation across multiple standard image datasets confirms the proposed method’s effectiveness, yielding ECC improvements up to 18.3% and ensuring high visual quality in downstream applications, particularly in challenging image areas with occlusions. For morphing-based applications, this leads to sharper, smoother transitions between image pairs, minimizing visual artifacts.en
dc.description.sponsorshipThis work is funded by the Federal Ministry of Education and Research (BMBF Germany, No. 01IS23007B)
dc.format8 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.doihttp://www.doi.org/10.24132/CSRN.2025-8
dc.identifier.issn2464-4617 (Print)
dc.identifier.issn2464-4625 (online)
dc.identifier.urihttp://hdl.handle.net/11025/62214
dc.language.isoenen
dc.publisherVaclav Skala - UNION Agencyen
dc.rights© Vaclav Skala - UNION Agencyen
dc.rights.accessopenAccessen
dc.subjectpočítačové viděnícs
dc.subjectzarovnání obrazucs
dc.subjectECCcs
dc.subjectobrazové korespondencecs
dc.subjectporovnávání rysůcs
dc.subjectevoluční optimalizacecs
dc.subject.translatedcomputer visionen
dc.subject.translatedimage alignmenten
dc.subject.translatedECCen
dc.subject.translatedimage correspondencesen
dc.subject.translatedfeature matchingen
dc.subject.translatedevolutionary optimizationen
dc.titleEGO-VC – Evolutionary GPU-Optimization of Visual Correspondences for Image Alignmenten
dc.typekonferenční příspěvekcs
dc.typeconferenceObjecten
dc.type.statusPeer revieweden
dc.type.versionpublishedVersionen
local.files.count1*
local.files.size3354475*
local.has.filesyes*

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
B02.pdf
Size:
3.2 MB
Format:
Adobe Portable Document Format
License bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: