EUVIMEDEUVIMED entdecken
Crossref

P‐2.4: End‐to‐End Neural Network for Cross‐Device 3D Display Content Conversion

Qin Cheng, HongBin Huang, ZhiYu Chen, Zi Wang, Qibin Feng, Guoqiang Lv

SID Symposium Digest of Technical Papers · 2026-08 · 57 (S1) · 1085-1087

DOI: 10.1002/sdtp.70003_291 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SID Symposium Digest of Technical Papers, online erschienen am 11.09.2026. Verfasst von Qin Cheng und 5 weiteren Autor:innen. Die Arbeit nennt 3 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a content conversion framework for autostereoscopic 3D displays based on slanted lenticular lens arrays, enabling LCD‐rendered multi‐view content to be mapped to mobile OLED screens with diamond subpixel layouts. Depth‐Image‐Based Rendering (DIBR) is employed to generate training data, and a compact U‐Net reconstructs multi‐view images from lenticular LCD content. The reconstructed views are then remapped to the diamond subpixel structure of the target OLED device. The effectiveness of the proposed method is experimentally validated on physical devices, demonstrating successful cross‐device content conversion and enabling multi‐view 3D display on the target OLED screen.

Zitieren

APA

Cheng, Q., Huang, H., Chen, Z., Wang, Z., Feng, Q., & Lv, G. (2026). P‐2.4: End‐to‐End Neural Network for Cross‐Device 3D Display Content Conversion. SID Symposium Digest of Technical Papers, 57(S1), 1085-1087. https://doi.org/10.1002/sdtp.70003_291

Vancouver

Cheng Q, Huang H, Chen Z, Wang Z, Feng Q, Lv G. P‐2.4: End‐to‐End Neural Network for Cross‐Device 3D Display Content Conversion. SID Symposium Digest of Technical Papers. 2026;57(S1):1085-1087. doi:10.1002/sdtp.70003_291

BibTeX
@article{Cheng2026,
  author = {Cheng, Qin and Huang, HongBin and Chen, ZhiYu and Wang, Zi and Feng, Qibin and Lv, Guoqiang},
  title = {P‐2.4: End‐to‐End Neural Network for Cross‐Device 3D Display Content Conversion},
  journal = {SID Symposium Digest of Technical Papers},
  year = {2026},
  volume = {57},
  number = {S1},
  pages = {1085--1087},
  doi = {10.1002/sdtp.70003_291}
}
Kostenlos starten →