BlitzGS: City-Scale Gaussian Splatting at Lightning Speed
2026-05-13 • Graphics
GraphicsComputer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce BlitzGS, a system that speeds up creating detailed 3D city models by managing many tiny 3D points called Gaussians across multiple graphics cards in a clever way. Instead of dividing by space, they divide by index to reduce repeated work. They also keep track of which points really matter for the current camera view and ignore the rest, making rendering faster. Tests show BlitzGS can build big city scenes much quicker without losing quality. The authors have shared their code online for others to use.
3D Gaussian Splattingdistributed renderingGPU shardinglevel of detail (LOD)visibility weightingimportance scoringcross-view cullingcity-scale reconstructionrendering optimization
Authors
Zhongtao Wang, Huishan Au, Yilong Li, Mai Su, Haojie Jin, Yisong Chen, Meng Gai, Fei Zhu, Guoping Wang
Abstract
We present BlitzGS, a distributed 3DGS framework that reduces active Gaussian workload for fast city-scale reconstruction. BlitzGS manages this workload at three coupled levels. At the system level, the framework shards Gaussians across GPUs by index parity rather than spatial blocks. This approach mitigates the cross-block visibility redundancy inherent in spatial partitioning. Furthermore, it distributes each rendering step through a single cross-GPU exchange that routes projected Gaussians to their tile owners. At the model level, scheduled importance-scoring passes shrink the global Gaussian population. During these passes, the framework generates a per-Gaussian visibility weight to bias density-control updates toward contributing primitives and a per-view importance mask for the view-level renderer. At the view level, BlitzGS trims each camera's active set with a distance-based LOD gate to exclude excessively fine primitives for the current frustum and the importance-based culling mask to skip Gaussians with negligible cross-view contribution. On large-scale benchmarks, BlitzGS matches the rendering quality of recent large-scale baselines while delivering an order-of-magnitude speedup, training city-scale scenes in tens of minutes. Our code is available at https: //github.com/AkierRaee/BlitzGS.