EUVIMEDEUVIMED entdecken
Crossref

ScaleGS: Closing the Gap between Real-time 3D Gaussian Splatting and Real-time XR Rendering

Kaiyan Chang, Yiming Gan, Wenlong Zhu, Kun Wang, Zhirong Chen, Yuan Cheng, Yinhe Han, Huawei Li, Ying Wang

ACM Transactions on Architecture and Code Optimization · 31.12.2025 · 22 (4) · 1-26

DOI: 10.1145/3774425 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Architecture and Code Optimization, online erschienen am 13.12.2025. Verfasst von Kaiyan Chang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Key R&D Program of China, NSFC, Beijing Municipal Science and Technology Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Photo-realistic rendering in XR applications using algorithms such as 3D Gaussian Splatting has been a bottleneck for real-time performance. GPUs do not provide efficient rendering, and most dedicated accelerators focus on single-object rendering, while nearly all XR scenarios involve multiple objects. We introduce ScaleGS , an algorithm-architecture co-design system designed to close the gap between real-time 3D Gaussian Splatting to real-time XR rendering. Specifically, we focus on multi-object rendering, structuring the XR rendering pipeline from an object-centric perspective and distinguishing static objects from moving ones to reduce unnecessary computations. Importantly, we identify multiple levels of parallelism across different objects and stages within the rendering pipeline, as well as high data reuse between objects within the render stage. Leveraging these insights, our acceleration framework comprises a runtime system, a micro-instruction scheduler, and a hardware accelerator. Extensive evaluations demonstrate that ScaleGS achieves comparable rendering quality to state-of-the-art dedicated 3D Gaussian Splatting accelerators, while improving throughput by 1.35× -2.14× compared with state-of-the-art rendering accelerators. 1

Förderung

  • National Key R&D Program of China
  • NSFC
  • Beijing Municipal Science and Technology Commission

Zitieren

APA

Chang, K., Gan, Y., Zhu, W., Wang, K., Chen, Z., Cheng, Y., Han, Y., Li, H., & Wang, Y. (2025). ScaleGS: Closing the Gap between Real-time 3D Gaussian Splatting and Real-time XR Rendering. ACM Transactions on Architecture and Code Optimization, 22(4), 1-26. https://doi.org/10.1145/3774425

Vancouver

Chang K, Gan Y, Zhu W, Wang K, Chen Z, Cheng Y, et al. ScaleGS: Closing the Gap between Real-time 3D Gaussian Splatting and Real-time XR Rendering. ACM Transactions on Architecture and Code Optimization. 2025;22(4):1-26. doi:10.1145/3774425

BibTeX
@article{Chang2025,
  author = {Chang, Kaiyan and Gan, Yiming and Zhu, Wenlong and Wang, Kun and Chen, Zhirong and Cheng, Yuan and Han, Yinhe and Li, Huawei and Wang, Ying},
  title = {ScaleGS: Closing the Gap between Real-time 3D Gaussian Splatting and Real-time XR Rendering},
  journal = {ACM Transactions on Architecture and Code Optimization},
  year = {2025},
  volume = {22},
  number = {4},
  pages = {1--26},
  doi = {10.1145/3774425}
}
Kostenlos starten →