SGSS: Streaming 6-DoF Navigation of Gaussian Splat Scenes
3D Gaussian Splatting (3DGS) is an emerging approach for training and representing real-world 3D scenes. Due to its photorealistic novel view synthesis and fast rendering speed (e.g., over 100 FPS), it has the potential to transform how scenes that can be explored in 6 degrees-of-freedom (6-DoF) are represented. However, a limiting factor of 3DGS is its large size, which requires high network bandwidth for streaming reconstructed real-world 3D scenes.
Authors
- M.T. Liu (ORCID: https://orcid.org/0009-0008-9669-2561)
- Mufeng Zhu (ORCID: https://orcid.org/0009-0000-9906-0836)
- Cunxi Yu (ORCID: https://orcid.org/0000-0003-3481-307X)
- Cheng-Hsin Hsu (ORCID: https://orcid.org/0000-0002-8116-2591)
- Yao Liu (ORCID: https://orcid.org/0000-0003-2817-0725)
Institutions
- Rutgers, The State University of New Jersey (US)
- National Tsing Hua University (TW)
- University of Maryland, College Park (US)
Publication Details
- Published
- 2025-03-26
- DOI
- https://doi.org/10.1145/3712676.3714437
- Citations
- 3
- Primary Topic
- Advanced Vision and Imaging
- Type
- article
- Field-Weighted Citation Impact
- 3.83
Funders
- National Science Foundation