测试时三维占用预测
Test-Time 3D Occupancy Prediction
利用视觉基础模型在测试时增量构建并优化3D高斯，再体素化为任意分辨率的占用预测，无需训练即可实现开放词表识别，为动态场景理解提供免训练、可适配的3D表示方案。
原文依据 incrementally constructs, optimizes, and voxelizes time-aware 3D Gaussians from raw sensor streams by integrating vision foundation models (VFMs) at runtime
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自监督三维占用预测为理解复杂驾驶场景提供了一种有前景的解决方案，无需昂贵的3D标注。然而，训练密集占用解码器以捕捉细粒度几何和语义可能需要数百个GPU小时，且一旦训练完成，此类模型难以适应变化的体素分辨率或新物体类别，除非进行大量重新训练。为克服这些限制，我们提出了一种实用且灵活的测试时占用预测框架，称为TT-Occ。我们的方法通过在运行时集成视觉基础模型（VFM），从原始传感器流中增量构建、优化并体素化时间感知的3D高斯。3D高斯的灵活表示支持在任意用户指定分辨率下进行体素化，而VFM的强大泛化能力支持准确的感知和开放词表识别，无需任何网络训练或微调。为验证我们框架的通用性和有效性，我们提出了两个变体：基于LiDAR的版本和以视觉为中心的版本，并在Occ3D-nuScenes和nuCraft基准上在不同体素分辨率下进行了大量实验。实验结果表明，TT-Occ显著优于现有的计算昂贵的预训练自监督对应方法。代码可在https://github.com/Xian-Bei/TT-Occ获取。
英文原文摘要 1421 字符
Self-supervised 3D occupancy prediction offers a promising solution for understanding complex driving scenes without requiring costly 3D annotations. However, training dense occupancy decoders to capture fine-grained geometry and semantics can demand hundreds of GPU hours, and once trained, such models struggle to adapt to varying voxel resolutions or novel object categories without extensive retraining. To overcome these limitations, we propose a practical and flexible test-time occupancy prediction framework termed TT-Occ. Our method incrementally constructs, optimizes, and voxelizes time-aware 3D Gaussians from raw sensor streams by integrating vision foundation models (VFMs) at runtime. The flexible representation of 3D Gaussians enables voxelization at arbitrary user-specified resolutions, while the strong generalization capability of VFMs supports accurate perception and open-vocabulary recognition without requiring any network training or fine-tuning. To validate the generality and effectiveness of our framework, we present two variants: a LiDAR-based version and a vision-centric version, and conduct extensive experiments on the Occ3D-nuScenes and nuCraft benchmarks under varying voxel resolutions. Experimental results show that TT-Occ significantly outperforms existing computationally expensive pretrained self-supervised counterparts. Code is available at https://github.com/Xian-Bei/TT-Occ.