.png){kind=icon}
.png){kind=icon}
Return
4DGStream: Variable Bitrate Dynamic Gaussian Splatting Streaming
.png){kind=icon}
PRE
AI
Z
D
L
M
J
B
M
F
J
DOI：10.1109/tmm.2026.3668629.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
While 3D Gaussian Splatting (3DGS) has revolutionized static scene representation, the extension to dynamic scene, i.e., 3DGS video (GSV), faces challenges related to reconstruction quality, rendering speed, and storage requirements. The substantial data volume of current GSV poses significant hurdles for streaming applications, particularly in the realm of AR, VR and MR. To tackle these challenges, we introduce <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4DGStream</monospace>, a novel framework that integrates an efficient GSV compression method, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Light4D</monospace>, and a bitrate adaptation streaming strategy, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">QoSmooth</monospace>, to ensure smooth playback while maintaining high visual quality. <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Light4D</monospace> employs a binarization-assisted spatiotemporal deformation network to model the deformation of Gaussian primitive attributes over time, while a spatiotemporal-aware masking module prunes trivial Gaussians, further enhancing long-term reconstruction quality. To reduce storage, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Light4D</monospace> uses a binary hash grid to model the entropy of attributes for arithmetic coding, with its binary nature allowing efficient entropy modeling via a Bernoulli distribution. These components enable <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Light4D</monospace> to improve the FPS/Storage metric by up to 12.4× over SpacetimeGS and 26.4× over 4DGS on the Neu3D dataset, with performance gains exceeding <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$3\times$</tex-math></inline-formula> orders of magnitude compared to other NeRF-based state-of-the-art (SOTA) methods. Here, FPS/Storage reflects the balance between rendering speed and data storage. Despite significant model size reductions, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Light4D</monospace> maintains or surpasses the reconstruction quality of 4DGS. Furthermore, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">QoSmooth</monospace> provides effective rate control to enhance playback smoothness, reducing bitrate level switches by 61.6% and increasing time-average utility by 26.2%. All these improvements make <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4DGStream</monospace> highly suited for GSV streaming, improving QoE by 36.7% compared to SOTA methods.
Keywords:
3D Gaussian splatting
compression
media streaming
quality of experience
virtual reality
Journal
IF:
9.7
Papers:
4.4K
Citations:
2.4W
Organization
Cited Papers