AI 中文总结
针对现有3D占用预测方法难以扩展到高体素分辨率的问题，提出高斯种子框架，通过分层设计规避内存瓶颈，构建TJScenes数据集，实验表明该方法在保持高精度的同时具有最低延迟，推动了高分辨率3D占用预测的效率-质量前沿。
AI 中文摘要
以视觉为中心的3D占用预测为自动驾驶和机器人导航提供了密集的场景表示，但由于计算成本过高，现有方法难以扩展到高体素分辨率。为了解决这个问题，我们引入了高斯种子，这是一个渐进式多尺度高斯占用预测框架，它将原语组织成一个从粗到细的层次结构。受益于这种分层设计，高斯种子有效地规避了密集表示中固有的内存瓶颈，成功扩展到0.1米的空间分辨率，同时保持实时推理能力。为了全面评估高分辨率几何感知，我们进一步构建了TJScenes，这是一个具有高度详细的0.1米注释的全景六相机占用数据集。在Occ3D-nuScenes和TJScenes上的大量实验表明，高斯种子在所有评估方法中具有最低的延迟，同时保持了极具竞争力的准确性，推动了高分辨率3D占用预测的效率-质量前沿。
英文摘要
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
