用分层高斯核实现高分辨率3D占位预测，兼顾速度与精度
GaussianSeed: Hierarchical Gaussian Seeding for High-Resolution 3D Occupancy Prediction
- 构建从粗到细的高斯核层级结构，降低内存瓶颈
- 在0.1米分辨率下实现实时推理，延迟最低
- 适用于自动驾驶和机器人导航的高精度场景理解
以视觉为中心的3D占位预测为自动驾驶与机器人导航提供密集场景表征，但现有方法因计算开销过大难以扩展至高体素分辨率。为此，我们提出GaussianSeed，一种分层多尺度高斯占位预测框架，将几何原语组织为由粗到细的层次结构。得益于该设计，GaussianSeed有效规避了密集表示固有的内存瓶颈，在保持实时推理能力的同时成功扩展至0.1m空间分辨率。为进一步评估高分辨率几何感知性能，我们构建了TJScenes，一个由六台全景相机组成的占位数据集，标注精度达0.1m。在Occ3D-nuScenes和TJScenes上的大量实验表明，GaussianSeed在所有对比方法中延迟最低，同时保持高度竞争力的准确性，推动了高分辨率3D占位预测的效率-质量边界。代码已开源：https://github.com/Athameral/GUSD
原文摘要 · Abstract (English)
Vision-centric 3D occupancy prediction provides dense scene representations essential for autonomous driving and robotic navigation, yet existing methods struggle to scale to high voxel resolutions due to prohibitive computational costs. To address this, we introduce GaussianSeed, a progressive multi-scale Gaussian occupancy prediction framework that organizes primitives into a coarse-to-fine hierarchy. Benefiting from this hierarchical design, GaussianSeed effectively circumvents the memory bottlenecks inherent in dense representations, successfully scaling to a $0.1\text{m}$ spatial resolution while maintaining real-time inference capabilities. To comprehensively evaluate high-resolution geometric perception, we further construct TJScenes, a panoramic six-camera occupancy dataset with highly detailed $0.1\text{m}$ annotations. Extensive experiments on Occ3D-nuScenes and TJScenes demonstrate that GaussianSeed delivers the lowest latency among all evaluated methods while maintaining highly competitive accuracy, advancing the efficiency-quality frontier of high-resolution 3D occupancy prediction. Codes are available at https://github.com/Athameral/GUSD
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。