EUVIMEDEUVIMED entdecken
Crossref

P‐3.12: Adaptive Frame Interpolation for Integral Imaging Video Generation

Xinyang Tong, Qiang Li, Hanlin Liu, Xiaorui Wang

SID Symposium Digest of Technical Papers · 2026-08 · 57 (S1) · 1128-1131

DOI: 10.1002/sdtp.70003_304 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SID Symposium Digest of Technical Papers, online erschienen am 11.09.2026. Verfasst von Xinyang Tong und 3 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Generating high‐frame‐rate element image arrays for 3D videos is crucial for integral imaging displays. Here, we propose a novel intermediate frame prediction method using Triple I‐3D Net. By dynamically constructing adaptive receptive fields, the method ensures that generated frames preserve strict internal optical logic. Furthermore, it integrates motion estimation and pixel synthesis within a unified loss function. Experiments show up to a 14.6% improvement in PSNR, a 35.5% enhancement in SSIM, and a 94% boost in LPIPS. This enables the efficient synthesis of high frame rate sequences, significantly enhancing dynamic 3D display performance.

Zitieren

APA

Tong, X., Li, Q., Liu, H., & Wang, X. (2026). P‐3.12: Adaptive Frame Interpolation for Integral Imaging Video Generation. SID Symposium Digest of Technical Papers, 57(S1), 1128-1131. https://doi.org/10.1002/sdtp.70003_304

Vancouver

Tong X, Li Q, Liu H, Wang X. P‐3.12: Adaptive Frame Interpolation for Integral Imaging Video Generation. SID Symposium Digest of Technical Papers. 2026;57(S1):1128-1131. doi:10.1002/sdtp.70003_304

BibTeX
@article{Tong2026,
  author = {Tong, Xinyang and Li, Qiang and Liu, Hanlin and Wang, Xiaorui},
  title = {P‐3.12: Adaptive Frame Interpolation for Integral Imaging Video Generation},
  journal = {SID Symposium Digest of Technical Papers},
  year = {2026},
  volume = {57},
  number = {S1},
  pages = {1128--1131},
  doi = {10.1002/sdtp.70003_304}
}
Kostenlos starten →