EUVIMEDEUVIMED entdecken
Crossref

Surfel-Based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction From Monocular Videos

Yiqun Zhao, Chenming Wu, Binbin Huang, Yihao Zhi, Chen Zhao, Jingdong Wang, Shenghua Gao

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-12 · 47 (12) · 11502-11518

DOI: 10.1109/tpami.2025.3599415 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-12. Verfasst von Yiqun Zhao und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Video Recording, Image Processing, Computer-Assisted, Imaging, Three-Dimensional. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 121 Literaturangaben. Gefördert von: General Research Fund of the Research Grants Council, National Natural Science Foundation of China, Program of Shanghai Academic Research Leader.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Efficient and accurate reconstruction of a relightable, dynamic clothed human avatar from a monocular video is crucial for the entertainment industry. This article presents SGIA (Surfel-based Gaussian Inverse Avatar), which introduces efficient training and rendering for relightable dynamic human reconstruction. SGIA advances previous Gaussian Avatar methods by comprehensively modeling Physically-Based Rendering (PBR) properties for clothed human avatars, allowing for the manipulation of avatars into novel poses under diverse lighting conditions. Specifically, our approach integrates pre-integration and image-based lighting for fast light calculations that surpass the performance of existing implicit-based techniques. To address challenges related to material lighting disentanglement and accurate geometry reconstruction, we propose an innovative occlusion approximation strategy and a progressive training approach. Extensive experiments demonstrate that SGIA not only achieves highly accurate physical properties but also significantly enhances the realistic relighting of dynamic human avatars, providing a substantial speed advantage.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Video RecordingImage Processing, Computer-AssistedImaging, Three-DimensionalHumansAlgorithmsNormal Distribution

Förderung

  • General Research Fund of the Research Grants Council
  • National Natural Science Foundation of China
  • Program of Shanghai Academic Research Leader
  • JC STEM Lab of Robotics for Soft Materials
  • The Hong Kong Jockey Club Charities Trust

Zitieren

APA

Zhao, Y., Wu, C., Huang, B., Zhi, Y., Zhao, C., Wang, J., & Gao, S. (2025). Surfel-Based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction From Monocular Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(12), 11502-11518. https://doi.org/10.1109/tpami.2025.3599415

Vancouver

Zhao Y, Wu C, Huang B, Zhi Y, Zhao C, Wang J, et al. Surfel-Based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction From Monocular Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(12):11502-11518. doi:10.1109/tpami.2025.3599415

BibTeX
@article{Zhao2025,
  author = {Zhao, Yiqun and Wu, Chenming and Huang, Binbin and Zhi, Yihao and Zhao, Chen and Wang, Jingdong and Gao, Shenghua},
  title = {Surfel-Based Gaussian Inverse Rendering for Fast and Relightable Dynamic Human Reconstruction From Monocular Videos},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {12},
  pages = {11502--11518},
  doi = {10.1109/tpami.2025.3599415}
}
Kostenlos starten →