GS-Cache: A GS-Cache Inference Framework for Large-scale Gaussian Splatting Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909503389171712 |
|---|---|
| author | Tao, Miao Zhou, Yuanzhen Xu, Haoran He, Zeyu Yang, Zhenyu Zhang, Yuchang Su, Zhongling Xu, Linning Ma, Zhenxiang Fu, Rong Li, Hengjie Zhang, Xingcheng Zhai, Jidong |
| author_facet | Tao, Miao Zhou, Yuanzhen Xu, Haoran He, Zeyu Yang, Zhenyu Zhang, Yuchang Su, Zhongling Xu, Linning Ma, Zhenxiang Fu, Rong Li, Hengjie Zhang, Xingcheng Zhai, Jidong |
| contents | Rendering large-scale 3D Gaussian Splatting (3DGS) model faces significant challenges in achieving real-time, high-fidelity performance on consumer-grade devices. Fully realizing the potential of 3DGS in applications such as virtual reality (VR) requires addressing critical system-level challenges to support real-time, immersive experiences. We propose GS-Cache, an end-to-end framework that seamlessly integrates 3DGS's advanced representation with a highly optimized rendering system. GS-Cache introduces a cache-centric pipeline to eliminate redundant computations, an efficiency-aware scheduler for elastic multi-GPU rendering, and optimized CUDA kernels to overcome computational bottlenecks. This synergy between 3DGS and system design enables GS-Cache to achieve up to 5.35x performance improvement, 35% latency reduction, and 42% lower GPU memory usage, supporting 2K binocular rendering at over 120 FPS with high visual quality. By bridging the gap between 3DGS's representation power and the demands of VR systems, GS-Cache establishes a scalable and efficient framework for real-time neural rendering in immersive environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14938 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GS-Cache: A GS-Cache Inference Framework for Large-scale Gaussian Splatting Models Tao, Miao Zhou, Yuanzhen Xu, Haoran He, Zeyu Yang, Zhenyu Zhang, Yuchang Su, Zhongling Xu, Linning Ma, Zhenxiang Fu, Rong Li, Hengjie Zhang, Xingcheng Zhai, Jidong Computer Vision and Pattern Recognition Rendering large-scale 3D Gaussian Splatting (3DGS) model faces significant challenges in achieving real-time, high-fidelity performance on consumer-grade devices. Fully realizing the potential of 3DGS in applications such as virtual reality (VR) requires addressing critical system-level challenges to support real-time, immersive experiences. We propose GS-Cache, an end-to-end framework that seamlessly integrates 3DGS's advanced representation with a highly optimized rendering system. GS-Cache introduces a cache-centric pipeline to eliminate redundant computations, an efficiency-aware scheduler for elastic multi-GPU rendering, and optimized CUDA kernels to overcome computational bottlenecks. This synergy between 3DGS and system design enables GS-Cache to achieve up to 5.35x performance improvement, 35% latency reduction, and 42% lower GPU memory usage, supporting 2K binocular rendering at over 120 FPS with high visual quality. By bridging the gap between 3DGS's representation power and the demands of VR systems, GS-Cache establishes a scalable and efficient framework for real-time neural rendering in immersive environments. |
| title | GS-Cache: A GS-Cache Inference Framework for Large-scale Gaussian Splatting Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.14938 |