Gau-Occ：几何补全高斯用于多模态三维占用预测
Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction
将场景表示为语义三维高斯锚框，用锚框引导的二维采样与跨模态对齐替代稠密体素融合，为视觉-激光雷达融合的占用预测提供了轻量化的几何引导方案。
原文依据 models the scene as a compact collection of semantic 3D Gaussians, enabling geometry-guided fusion without dense volumetric processing
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维语义占用预测对自动驾驶至关重要，然而纯视觉方法几何线索较弱，现有多模态框架往往依赖稠密的体素或鸟瞰图张量，带来沉重的计算开销。本文提出 Gau-Occ，一个多模态框架，将场景建模为紧凑的语义三维高斯集合，从而无需稠密体素处理即可实现几何引导的融合。为增强几何完整性，一个在真实世界先验上训练的学习型激光雷达补全扩散器（LCD）从稀疏激光雷达中恢复缺失结构，补全后的点被编码为语义高斯锚框。为进一步整合多视角图像语义，我们引入高斯锚框融合（GAF），一个几何对齐的聚合模块，执行锚框引导的二维采样、局部邻域编码与跨模态对齐。通过构建捕获空间一致性与语义判别性的局部聚合高斯描述子，GAF 促进了跨模态的准确特征关联。通过对高斯属性的锚框驱动细化，Occ-GS 支持精细的三维占用预测。在具有挑战性的基准上的大量实验表明，Occ-GS 取得了最优性能。
英文原文摘要 1282 字符
3D semantic occupancy prediction is crucial for autonomous driving, yet vision-only approaches suffer from weak geometric cues, and existing multi-modal frameworks often depend on dense voxel or BEV tensors that impose heavy computational cost. We present Gau-Occ, a multi-modal framework that models the scene as a compact collection of semantic 3D Gaussians, enabling geometry-guided fusion without dense volumetric processing. To enhance geometric completeness, a learned LiDAR Completion Diffuser (LCD) trained on real-world priors recovers missing structures from sparse LiDAR, and the completed points are encoded as semantic Gaussian anchors. To further integrate multi-view image semantics, we introduce Gaussian Anchor Fusion (GAF), a geometry-aligned aggregation module that performs anchor-guided 2D sampling, local neighborhood encoding, and cross-modal alignment. By constructing locally aggregated Gaussian descriptors that capture spatial consistency and semantic discriminability, GAF facilitates accurate feature association across modalities. Through anchor-driven refinement of Gaussian attributes, Occ-GS supports detailed 3D occupancy prediction. Extensive experiments across challenging benchmarks demonstrate that Occ-GS achieves state-of-the-art performance.