EUVIMEDEUVIMED entdecken
Crossref

Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture

Julien Philip, Li Ma, Pascal Clausen, Wenqi Xian, Ahmet Levent Taşel, Mingming He, Xueming Yu, David M. George, Ning Yu, Oliver Pilarski, Paul Debevec

ACM Transactions on Graphics · 2025-12 · 44 (6) · 1-13

DOI: 10.1145/3763336 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 04.12.2025. Verfasst von Julien Philip und 10 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 122 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a unique system for large-scale, multi-performer, high resolution 4D volumetric capture providing realistic free-viewpoint video up to and including 4K resolution facial closeups. To achieve this, we employ a novel volumetric capture, reconstruction and rendering pipeline based on Dynamic Gaussian Splatting and Diffusion-based Detail Enhancement. We design our pipeline specifically to meet the demands of high-end media production. We employ two capture rigs: the Scene Rig , which captures multi-actor performances at a resolution which falls short of 4K production quality, and the Face Rig , which records high-fidelity single-actor facial detail to serve as a reference for detail enhancement. We first reconstruct dynamic performances from the Scene Rig using 4D Gaussian Splatting, incorporating new model designs and training strategies to improve reconstruction, dynamic range, and rendering quality. Then to render high-quality images for facial closeups, we introduce a diffusion-based detail enhancement model. This model is fine-tuned with high-fidelity data from the same actors recorded in the Face Rig. We train on paired data generated from low- and high-quality Gaussian Splatting (GS) models, using the low-quality input to match the quality of the Scene Rig , with the high-quality GS as ground truth. Our results demonstrate the effectiveness of this pipeline in bridging the gap between the scalable performance capture of a large-scale rig and the high-resolution standards required for film and media production.

Zitieren

APA

Philip, J., Ma, L., Clausen, P., Xian, W., Taşel, A. L., He, M., Yu, X., George, D. M., Yu, N., Pilarski, O., & Debevec, P. (2025). Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture. ACM Transactions on Graphics, 44(6), 1-13. https://doi.org/10.1145/3763336

Vancouver

Philip J, Ma L, Clausen P, Xian W, Taşel AL, He M, et al. Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture. ACM Transactions on Graphics. 2025;44(6):1-13. doi:10.1145/3763336

BibTeX
@article{Philip2025,
  author = {Philip, Julien and Ma, Li and Clausen, Pascal and Xian, Wenqi and Taşel, Ahmet Levent and He, Mingming and Yu, Xueming and George, David M. and Yu, Ning and Pilarski, Oliver and Debevec, Paul},
  title = {Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture},
  journal = {ACM Transactions on Graphics},
  year = {2025},
  volume = {44},
  number = {6},
  pages = {1--13},
  doi = {10.1145/3763336}
}
Kostenlos starten →