LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Xinhui, Wang, Can, Liu, Lei, Chen, Zhenghao, Jiang, Wei, Wang, Wei, Xu, Dong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912849752752128
author Liu, Xinhui
Wang, Can
Liu, Lei
Chen, Zhenghao
Jiang, Wei
Wang, Wei
Xu, Dong
author_facet Liu, Xinhui
Wang, Can
Liu, Lei
Chen, Zhenghao
Jiang, Wei
Wang, Wei
Xu, Dong
contents Free-Viewpoint Video (FVV) reconstruction enables photorealistic and interactive 3D scene visualization; however, real-time streaming is often bottlenecked by sparse-view inputs, prohibitive training costs, and bandwidth constraints. While recent 3D Gaussian Splatting (3DGS) has advanced FVV due to its superior rendering speed, Streaming Free-Viewpoint Video (SFVV) introduces additional demands for rapid optimization, high-fidelity reconstruction under sparse constraints, and minimal storage footprints. To bridge this gap, we propose StreamLoD-GS, an LoD-based Gaussian Splatting framework designed specifically for SFVV. Our approach integrates three core innovations: 1) an Anchor- and Octree-based LoD-structured 3DGS with a hierarchical Gaussian dropout technique to ensure efficient and stable optimization while maintaining high-quality rendering; 2) a GMM-based motion partitioning mechanism that separates dynamic and static content, refining dynamic regions while preserving background stability; and 3) a quantized residual refinement framework that significantly reduces storage requirements without compromising visual fidelity. Extensive experiments demonstrate that StreamLoD-GS achieves competitive or state-of-the-art performance in terms of quality, efficiency, and storage.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18475
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction
Liu, Xinhui
Wang, Can
Liu, Lei
Chen, Zhenghao
Jiang, Wei
Wang, Wei
Xu, Dong
Graphics
Computer Vision and Pattern Recognition
Free-Viewpoint Video (FVV) reconstruction enables photorealistic and interactive 3D scene visualization; however, real-time streaming is often bottlenecked by sparse-view inputs, prohibitive training costs, and bandwidth constraints. While recent 3D Gaussian Splatting (3DGS) has advanced FVV due to its superior rendering speed, Streaming Free-Viewpoint Video (SFVV) introduces additional demands for rapid optimization, high-fidelity reconstruction under sparse constraints, and minimal storage footprints. To bridge this gap, we propose StreamLoD-GS, an LoD-based Gaussian Splatting framework designed specifically for SFVV. Our approach integrates three core innovations: 1) an Anchor- and Octree-based LoD-structured 3DGS with a hierarchical Gaussian dropout technique to ensure efficient and stable optimization while maintaining high-quality rendering; 2) a GMM-based motion partitioning mechanism that separates dynamic and static content, refining dynamic regions while preserving background stability; and 3) a quantized residual refinement framework that significantly reduces storage requirements without compromising visual fidelity. Extensive experiments demonstrate that StreamLoD-GS achieves competitive or state-of-the-art performance in terms of quality, efficiency, and storage.
title LoD-Structured 3D Gaussian Splatting for Streaming Video Reconstruction
topic Graphics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.18475