STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Chenqi, Feng, Yu, Zhao, Jieru, Liu, Guangda, Ding, Wenchao, Wu, Chentao, Guo, Minyi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912424354906112
author Zhang, Chenqi
Feng, Yu
Zhao, Jieru
Liu, Guangda
Ding, Wenchao
Wu, Chentao
Guo, Minyi
author_facet Zhang, Chenqi
Feng, Yu
Zhao, Jieru
Liu, Guangda
Ding, Wenchao
Wu, Chentao
Guo, Minyi
contents 3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 frames per second (FPS) on resource-constrained mobile devices, achieving only 2 to 9 FPS.Existing accelerators focus on compute efficiency but overlook memory efficiency, leading to redundant DRAM traffic. We introduce STREAMINGGS, a fully streaming 3DGS algorithm-architecture co-design that achieves fine-grained pipelining and reduces DRAM traffic by transforming from a tile-centric rendering to a memory-centric rendering. Results show that our design achieves up to 45.7 $\times$ speedup and 62.9 $\times$ energy savings over mobile Ampere GPUs.
format Preprint
id arxiv_https___arxiv_org_abs_2506_09070
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support
Zhang, Chenqi
Feng, Yu
Zhao, Jieru
Liu, Guangda
Ding, Wenchao
Wu, Chentao
Guo, Minyi
Graphics
Artificial Intelligence
3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 frames per second (FPS) on resource-constrained mobile devices, achieving only 2 to 9 FPS.Existing accelerators focus on compute efficiency but overlook memory efficiency, leading to redundant DRAM traffic. We introduce STREAMINGGS, a fully streaming 3DGS algorithm-architecture co-design that achieves fine-grained pipelining and reduces DRAM traffic by transforming from a tile-centric rendering to a memory-centric rendering. Results show that our design achieves up to 45.7 $\times$ speedup and 62.9 $\times$ energy savings over mobile Ampere GPUs.
title STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support
topic Graphics
Artificial Intelligence
url https://arxiv.org/abs/2506.09070