A photo to generative AI workflow for rapid 3D heritage representations

Basit Öğe Kaydı
dc.authorid0009-0007-7369-8576
dc.authorid0000-0002-2660-0106
dc.authorid0000-0002-7327-9810
dc.authorid0000-0002-9517-7313
dc.contributor.authorAş Çemrek, Handan
dc.contributor.authorIşıkdağ, Ümit
dc.contributor.authorBekdaş, Gebrail
dc.contributor.authorNiğdeli, Sinan Melih
dc.date.accessioned2026-08-21T17:00:36Z
dc.date.available2026-08-21T17:00:36Z
dc.date.issued2026
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Mimarlık Bölümü
dc.description.abstractThis paper investigates generative AI workflows that reconstruct 3D architectural heritage models from a single photograph. We compare two pipelines that combine a 2D image model with Tencent’s Hunyuan3D 2.1 image-to-3D system: (1) Gemini Flash 2.5 + Hunyuan3D and (2) Qwen-Image-Edit + Hunyuan3D. Using a dataset of 16 Turkish architectural landmarks photographed from sub-optimal viewpoints, each method first generates an isometric or gently re-angled view and then produces a PBR-textured GLB mesh approximating LOD3 building detail. The pipelines are evaluated in terms of visual fidelity of intermediate images, geometric completeness and sharpness of the 3D meshes, dimensional consistency, processing time, user experience, and downstream compatibility with BIM, GIS, VR and web viewers. Results show that both workflows deliver photorealistic, lightweight 3D assets within minutes, dramatically lowering the cost and expertise barrier compared with conventional photogrammetry or laser scanning. The Qwen-based pipeline better preserves original textures and colors, enriches side-facade information, and offers higher reproducibility thanks to its open-source model and public interfaces. The Gemini-based pipeline provides cleaner, stylized views but is constrained by closed access. We conclude by positioning single-image generative AI as a rapid, complementary tool for cultural heritage visualization, education and preliminary digital twin creation rather than a substitute for metric survey.
dc.identifier.citationAş Çemrek, H., Işıkdağ, Ü., Bekdaş, G., & Niğdeli, S. M. (2026). A photo to generative AI workflow for rapid 3D heritage representations. Hassanien, A. E., Anand, S., Jaiswal, A., Kumar, P. (Eds.), Innovative Computing and Communications, pp. 296-305. Springer Nature Link. https://doi.org/10.1007/978-3-032-28310-8_21
dc.identifier.doi10.1007/978-3-032-28310-8_21
dc.identifier.endpage305
dc.identifier.isbn9783032283092
dc.identifier.isbn9783032283108
dc.identifier.scopus2-s2.0-105047334389
dc.identifier.startpage296
dc.identifier.urihttps://doi.org/10.1007/978-3-032-28310-8_21
dc.identifier.urihttps://hdl.handle.net/20.500.13055/1596
dc.institutionauthorAş Çemrek, Handan
dc.institutionauthorid0009-0007-7369-8576
dc.language.isoen
dc.publisherSpringer Nature Link
dc.relation.ispartofInnovative Computing and Communications
dc.relation.publicationcategoryKonferans Öğesi - Ulusal - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectImage Processing
dc.subjectThree-Dimensional Imaging
dc.subjectTime-lapse Imaging
dc.subjectVisual Culture
dc.subjectVisual Journalism
dc.subject3-D Image Reconstruction
dc.titleA photo to generative AI workflow for rapid 3D heritage representations
dc.typeConference Object
dspace.entity.typePublication
relation.isAuthorOfPublication3d4c367d-8571-48a0-b589-d42dd5f6db30
relation.isAuthorOfPublication.latestForDiscovery3d4c367d-8571-48a0-b589-d42dd5f6db30

Dosyalar

Lisans paketi
Listeleniyor 1 - 1 / 1
Kapalı Erişim
İsim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Mimarlık Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu