Adaptive 3D Gaussian Splatting Video Streaming
🤖 AI Summary
To address the challenges of large data volume and high complexity in compression and streaming of 3D Gaussian Splatting (3DGS) video, this paper proposes an adaptive streaming framework. The method jointly models 3D Gaussian point clouds, estimates a Gaussian-based deformation field for spatiotemporal coherence, and integrates saliency-aware tiling with differential quality modeling to enable bandwidth-adaptive scheduling. Key contributions include: (1) a spatiotemporally consistent video representation built upon a learned Gaussian deformation field; and (2) a hybrid saliency-driven tiling strategy coupled with rate-distortion-optimized, content-adaptive quality assignment. Experimental results demonstrate that the framework achieves an average BD-rate reduction of 18.7%, a PSNR gain of 2.1 dB, and a 32% decrease in transmission latency, significantly outperforming state-of-the-art 3DGS video streaming approaches.
Application Category
📝 Abstract
The advent of 3D Gaussian splatting (3DGS) has significantly enhanced the quality of volumetric video representation. Meanwhile, in contrast to conventional volumetric video, 3DGS video poses significant challenges for streaming due to its substantially larger data volume and the heightened complexity involved in compression and transmission. To address these issues, we introduce an innovative framework for 3DGS volumetric video streaming. Specifically, we design a 3DGS video construction method based on the Gaussian deformation field. By employing hybrid saliency tiling and differentiated quality modeling of 3DGS video, we achieve efficient data compression and adaptation to bandwidth fluctuations while ensuring high transmission quality. Then we build a complete 3DGS video streaming system and validate the transmission performance. Through experimental evaluation, our method demonstrated superiority over existing approaches in various aspects, including video quality, compression effectiveness, and transmission rate.
Problem
Research questions and friction points this paper is trying to address.
Streaming large-volume 3DGS video efficiently
Compressing 3DGS data with quality adaptation
Handling bandwidth fluctuations during transmission
Innovation
Methods, ideas, or system contributions that make the work stand out.
3DGS video construction via Gaussian deformation field
Hybrid saliency tiling for efficient compression
Differentiated quality modeling for bandwidth adaptation
🔎 Similar Papers
No similar papers found.
