{"ID":2825900,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20495","arxiv_id":"2512.20495","title":"Nebula: Enable City-Scale 3D Gaussian Splatting in Virtual Reality via Collaborative Rendering and Accelerated Stereo Rasterization","abstract":"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.","short_abstract":"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 s...","url_abs":"https://arxiv.org/abs/2512.20495","url_pdf":"https://arxiv.org/pdf/2512.20495v1","authors":"[\"He Zhu\",\"Zheng Liu\",\"Xingyang Li\",\"Anbang Wu\",\"Jieru Zhao\",\"Fangxin Liu\",\"Yiming Gan\",\"Jingwen Leng\",\"Yu Feng\"]","published":"2025-12-23T16:42:14Z","proceeding":"cs.AR","tasks":"[\"cs.AR\"]","methods":"[]","has_code":false}