TY - GEN
T1 - LTS
T2 - 16th ACM Multimedia Systems Conference, MMSys 2025
AU - Sun, Yuan Chun
AU - Shi, Yuang
AU - Lee, Cheng Tse
AU - Zhu, Mufeng
AU - Ooi, Wei Tsang
AU - Liu, Yao
AU - Huang, Chun Ying
AU - Hsu, Cheng Hsin
N1 - Publisher Copyright:
© 2025 Copyright is held by the owner/author(s). Publication rights licensed to ACM.
PY - 2025/3/31
Y1 - 2025/3/31
N2 - We present a novel DASH-based streaming system for dynamic 3D Gaussian Splatting (3DGS) scenes, addressing the challenges of streaming large amounts of 3DGS data over diverse and dynamic networks. Our Layer, Tile, and Segment Adaptive streaming (LTS) system combines three key features: (i) multi-layer streaming, which adapts to diverse client capabilities while balancing visual quality and bandwidth usage, (ii) tiled streaming, which reduces unnecessary data transmission by focusing on the user's viewport, and (iii) segment streaming, which divides dynamic 3DGS scenes into segments, letting clients request them dynamically to handle network fluctuations. Our experimental results demonstrate that our LTS system achieves superior performance in both live and on-demand streaming of dynamic 3DGS scenes compared to the baselines. For example, in live streaming, LTS could achieve up to 99.70% reduction in missing frames on average and deliver a maximum PSNR (Peak Signal-to-Noise Ratio) improvement of 10.08 dB. In on-demand streaming, LTS could reduce the freeze time by up to 92.01%, and increase the synthesized view quality by up to 5.14 dB in PSNR and 0.11 in SSIM (Structural Similarity Index). Our source codes are available at: https://github.com/AIINS-NTHU/LTS-DASH-Streaming-System-for-3DGS.
AB - We present a novel DASH-based streaming system for dynamic 3D Gaussian Splatting (3DGS) scenes, addressing the challenges of streaming large amounts of 3DGS data over diverse and dynamic networks. Our Layer, Tile, and Segment Adaptive streaming (LTS) system combines three key features: (i) multi-layer streaming, which adapts to diverse client capabilities while balancing visual quality and bandwidth usage, (ii) tiled streaming, which reduces unnecessary data transmission by focusing on the user's viewport, and (iii) segment streaming, which divides dynamic 3DGS scenes into segments, letting clients request them dynamically to handle network fluctuations. Our experimental results demonstrate that our LTS system achieves superior performance in both live and on-demand streaming of dynamic 3DGS scenes compared to the baselines. For example, in live streaming, LTS could achieve up to 99.70% reduction in missing frames on average and deliver a maximum PSNR (Peak Signal-to-Noise Ratio) improvement of 10.08 dB. In on-demand streaming, LTS could reduce the freeze time by up to 92.01%, and increase the synthesized view quality by up to 5.14 dB in PSNR and 0.11 in SSIM (Structural Similarity Index). Our source codes are available at: https://github.com/AIINS-NTHU/LTS-DASH-Streaming-System-for-3DGS.
KW - adaptive bitrate algorithm
KW - multi-layer representation
KW - streaming
KW - volumetric video
UR - https://www.scopus.com/pages/publications/105005023707
UR - https://www.scopus.com/pages/publications/105005023707#tab=citedBy
U2 - 10.1145/3712676.3714445
DO - 10.1145/3712676.3714445
M3 - Conference contribution
AN - SCOPUS:105005023707
T3 - MMSys 2025 - Proceedings of the 16th ACM Multimedia Systems Conference
SP - 136
EP - 147
BT - MMSys 2025 - Proceedings of the 16th ACM Multimedia Systems Conference
PB - Association for Computing Machinery, Inc
Y2 - 31 March 2025 through 3 April 2025
ER -