EUVIMEDEUVIMED entdecken
Crossref

Efficient and User-Friendly Visualization of Neural Relightable Images for Cultural Heritage Applications

Leonardo Righetto, Mohammad Khademizadeh, Andrea Giachetti, Federico Ponchio, Davit Gigilashvili, Fabio Bettio, Enrico Gobbetti

Journal on Computing and Cultural Heritage · 31.12.2024 · 17 (4) · 1-24

DOI: 10.1145/3690390 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal on Computing and Cultural Heritage, online erschienen am 07.12.2024. Verfasst von Leonardo Righetto und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: European Union Next-GenerationEU (Piano Nazionale di Ripresa e Resilienza (PNRR) – Missione 4 Componente 2, Investimento 1.5 – D.D., REFLEX – REFLectance EXploration: improving the acquisition, distribution, and exploration of multi-light image collections for surface characterization and an…, EU Next-GenerationEU PNRR, componente M4C2, investimento 1.1..

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We introduce an innovative multi-resolution framework for encoding and interactively visualizing large relightable images using a neural reflectance model derived from a state-of-the-art technique. The framework is seamlessly integrated into a scalable multi-platform framework that supports adaptive streaming and exploration of multi-layered relightable models in web settings. To enhance efficiency, we optimized the neural model, simplified decoding, and implemented a custom WebGL shader specific to the task, eliminating the need for deep-learning library integration in the code. Additionally, we introduce an efficient level-of-detail management system supporting fine-grained adaptive rendering through on-the-fly resampling in latent feature space. The resulting viewer facilitates interactive neural relighting of large images. Its modular design allows the incorporation of functionalities for cultural heritage analysis, such as loading and simultaneous visualization of multiple relightable layers with arbitrary rotations.

Förderung

  • European Union Next-GenerationEU (Piano Nazionale di Ripresa e Resilienza (PNRR) – Missione 4 Componente 2, Investimento 1.5 – D.D.
  • REFLEX – REFLectance EXploration: improving the acquisition, distribution, and exploration of multi-light image collections for surface characterization and an…
  • EU Next-GenerationEU PNRR, componente M4C2, investimento 1.1.

Zitieren

APA

Righetto, L., Khademizadeh, M., Giachetti, A., Ponchio, F., Gigilashvili, D., Bettio, F., & Gobbetti, E. (2024). Efficient and User-Friendly Visualization of Neural Relightable Images for Cultural Heritage Applications. Journal on Computing and Cultural Heritage, 17(4), 1-24. https://doi.org/10.1145/3690390

Vancouver

Righetto L, Khademizadeh M, Giachetti A, Ponchio F, Gigilashvili D, Bettio F, et al. Efficient and User-Friendly Visualization of Neural Relightable Images for Cultural Heritage Applications. Journal on Computing and Cultural Heritage. 2024;17(4):1-24. doi:10.1145/3690390

BibTeX
@article{Righetto2024,
  author = {Righetto, Leonardo and Khademizadeh, Mohammad and Giachetti, Andrea and Ponchio, Federico and Gigilashvili, Davit and Bettio, Fabio and Gobbetti, Enrico},
  title = {Efficient and User-Friendly Visualization of Neural Relightable Images for Cultural Heritage Applications},
  journal = {Journal on Computing and Cultural Heritage},
  year = {2024},
  volume = {17},
  number = {4},
  pages = {1--24},
  doi = {10.1145/3690390}
}
Kostenlos starten →