Nebula: Enable City-Scale 3D Gaussian Splatting in Virtual Reality via Collaborative Rendering and Accelerated Stereo Rasterization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911335396147200 |
|---|---|
| author | Zhu, He Liu, Zheng Li, Xingyang Wu, Anbang Zhao, Jieru Liu, Fangxin Gan, Yiming Leng, Jingwen Feng, Yu |
| author_facet | Zhu, He Liu, Zheng Li, Xingyang Wu, Anbang Zhao, Jieru Liu, Fangxin Gan, Yiming Leng, Jingwen Feng, Yu |
| contents | 3D Gaussian splatting (3DGS) has drawn significant attention in the architectural community recently. However, current architectural designs often overlook the 3DGS scalability, making them fragile for extremely large-scale 3DGS. Meanwhile, the VR bandwidth requirement makes it impossible to deliver high-fidelity and smooth VR content from the cloud.
We present Nebula, a coherent acceleration framework for large-scale 3DGS collaborative rendering. Instead of streaming videos, Nebula streams intermediate results after the LoD search, reducing 1925% data communication between the cloud and the client. To further enhance the motion-to-photon experience, we introduce a temporal-aware LoD search in the cloud that tames the irregular memory access and reduces redundant data access by exploiting temporal coherence across frames. On the client side, we propose a novel stereo rasterization that enables two eyes to share most computations during the stereo rendering with bit-accurate quality. With minimal hardware augmentations, Nebula achieves 2.7$\times$ motion-to-photon speedup and reduces 1925% bandwidth over lossy video streaming. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20495 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Nebula: Enable City-Scale 3D Gaussian Splatting in Virtual Reality via Collaborative Rendering and Accelerated Stereo Rasterization Zhu, He Liu, Zheng Li, Xingyang Wu, Anbang Zhao, Jieru Liu, Fangxin Gan, Yiming Leng, Jingwen Feng, Yu Hardware Architecture 3D Gaussian splatting (3DGS) has drawn significant attention in the architectural community recently. However, current architectural designs often overlook the 3DGS scalability, making them fragile for extremely large-scale 3DGS. Meanwhile, the VR bandwidth requirement makes it impossible to deliver high-fidelity and smooth VR content from the cloud. We present Nebula, a coherent acceleration framework for large-scale 3DGS collaborative rendering. Instead of streaming videos, Nebula streams intermediate results after the LoD search, reducing 1925% data communication between the cloud and the client. To further enhance the motion-to-photon experience, we introduce a temporal-aware LoD search in the cloud that tames the irregular memory access and reduces redundant data access by exploiting temporal coherence across frames. On the client side, we propose a novel stereo rasterization that enables two eyes to share most computations during the stereo rendering with bit-accurate quality. With minimal hardware augmentations, Nebula achieves 2.7$\times$ motion-to-photon speedup and reduces 1925% bandwidth over lossy video streaming. |
| title | Nebula: Enable City-Scale 3D Gaussian Splatting in Virtual Reality via Collaborative Rendering and Accelerated Stereo Rasterization |
| topic | Hardware Architecture |
| url | https://arxiv.org/abs/2512.20495 |