EUVIMEDEUVIMED entdecken
Crossref

85‐3: Invited Paper: Lens‐Based CGEI Algorithm with GPU Acceleration for Integral Imaging Light‐Field Displays System

Shao-Yu Hung, Hoang-Yan Lin

SID Symposium Digest of Technical Papers · 2026-06 · 57 (1) · 1176-1179

DOI: 10.1002/sdtp.70001_318 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SID Symposium Digest of Technical Papers, online erschienen am 11.09.2026. Verfasst von Shao-Yu Hung und 1 weiteren Autor:innen. Die Arbeit nennt 3 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automotive Augmented Reality (AR) displays demand low‐latency elemental image generation for safety‐critical cues. However, conventional pixel‐wise Computer Generated Elemental Image (CGEI) methods are impractical for dynamic scenes due to high computational costs. We propose a dynamic synthesis pipeline integrating skeletonization‐based trajectory extraction with a lens‐based LUT framework. By utilizing a Unified Mask Stack and optimized PTX CUDA kernels, our method achieves single‐pass multi‐depth synthesis. Experiments show a generation time of just 0.032 s while maintaining high image quality (SSIM > 0.91), validating the system's potential for approaching real‐time automotive AR.

Zitieren

APA

Hung, S., & Lin, H. (2026). 85‐3: Invited Paper: Lens‐Based CGEI Algorithm with GPU Acceleration for Integral Imaging Light‐Field Displays System. SID Symposium Digest of Technical Papers, 57(1), 1176-1179. https://doi.org/10.1002/sdtp.70001_318

Vancouver

Hung S, Lin H. 85‐3: Invited Paper: Lens‐Based CGEI Algorithm with GPU Acceleration for Integral Imaging Light‐Field Displays System. SID Symposium Digest of Technical Papers. 2026;57(1):1176-1179. doi:10.1002/sdtp.70001_318

BibTeX
@article{Hung2026,
  author = {Hung, Shao-Yu and Lin, Hoang-Yan},
  title = {85‐3: Invited Paper: Lens‐Based CGEI Algorithm with GPU Acceleration for Integral Imaging Light‐Field Displays System},
  journal = {SID Symposium Digest of Technical Papers},
  year = {2026},
  volume = {57},
  number = {1},
  pages = {1176--1179},
  doi = {10.1002/sdtp.70001_318}
}
Kostenlos starten →