EUVIMEDEUVIMED entdecken
Crossref

High‐Fidelity Multi‐View Normal Integration With Scale‐Encoded Neural Surface Representation

Tongyu Yang, Heng Guo, Yasuyuki Matsushita, Fumio Okura, Yu Luo, Xin Fan

Computer Graphics Forum · 30.03.2026

DOI: 10.1111/cgf.70427 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 30.03.2026. Verfasst von Tongyu Yang und 5 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Liaoning Province, China Scholarship Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Previous multi‐view normal integration methods typically sample a single ray per pixel, without considering the spatial area covered by each pixel, which varies with camera intrinsics and the camera‐to‐object distance. Consequently, when the target object is captured at different distances, the normals at corresponding pixels may differ across views. This multi‐view surface normal inconsistency results in the blurring of high‐frequency details in the reconstructed surface. To address this issue, we propose a scale‐encoded neural surface representation (SNSR) that incorporates the pixel coverage area into the neural representation. By associating each 3D point with a spatial scale and calculating its normal from a hybrid grid‐based encoding, our method effectively represents multi‐scale surface normals captured at varying distances. Furthermore, to enable scale‐aware surface reconstruction, we introduce a mesh extraction module that assigns an optimal local scale to each vertex based on the training observations. Experimental results demonstrate that our approach consistently yields high‐fidelity surface reconstruction from normals observed at varying distances, outperforming existing multi‐view normal integration methods.

Förderung

  • National Natural Science Foundation of China
  • Key Research and Development Program of Liaoning Province
  • China Scholarship Council

Zitieren

APA

Yang, T., Guo, H., Matsushita, Y., Okura, F., Luo, Y., & Fan, X. (2026). High‐Fidelity Multi‐View Normal Integration With Scale‐Encoded Neural Surface Representation. Computer Graphics Forum. https://doi.org/10.1111/cgf.70427

Vancouver

Yang T, Guo H, Matsushita Y, Okura F, Luo Y, Fan X. High‐Fidelity Multi‐View Normal Integration With Scale‐Encoded Neural Surface Representation. Computer Graphics Forum. 2026. doi:10.1111/cgf.70427

BibTeX
@article{Yang2026,
  author = {Yang, Tongyu and Guo, Heng and Matsushita, Yasuyuki and Okura, Fumio and Luo, Yu and Fan, Xin},
  title = {High‐Fidelity Multi‐View Normal Integration With Scale‐Encoded Neural Surface Representation},
  journal = {Computer Graphics Forum},
  year = {2026},
  doi = {10.1111/cgf.70427}
}
Kostenlos starten →