将视觉几何先验泛化到稀疏高斯占用预测
Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction
把 VGGT 这类可泛化视觉几何模型输出的表面点沿相机射线向内扩展成体素采样，并用高斯原语做概率化占用推断，为单目/流式占用预测提供了一条不依赖体素密集监督、可直接复用几何基础模型先验的路线。
原文依据 extends surface points inward along camera rays to generate volumetric samples, which are represented as Gaussian primitives for probabilistic occupancy inference
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论准确的 3D 场景理解对具身智能至关重要，占用预测正成为推理物体与自由空间的关键任务。现有方法主要依赖深度先验（如 DepthAnything），但对 3D 线索的利用十分有限，限制了性能与泛化能力。近期，VGGT 等视觉几何模型已展现出提供丰富 3D 先验的强大能力，但与单目深度基础模型类似，它们仍只作用于可见表面层面，而非体内部，这促使我们探索如何更有效地利用这些日益强大的几何先验进行 3D 占用预测。我们提出 GPOcc，一个利用可泛化视觉几何先验（GPs）进行单目占用预测的框架。该方法沿相机射线将表面点向内扩展以生成体素采样，并将其表示为高斯原语以进行概率化占用推断。为处理流式输入，我们进一步设计了一种免训练的增量更新策略，将逐帧高斯融合为统一的全局表示。在 Occ-ScanNet 与 EmbodiedOcc-ScanNet 上的实验显示出显著提升：相比此前的最先进方法，GPOcc 在单目设定下平均交并比提升 +9.99，在流式设定下提升 +11.79。在相同深度先验下，它以 2.65 倍的速度运行，同时平均交并比提升 +6.73。这些结果表明 GPOcc 更有效且更高效地利用了几何先验。代码将发布于 https://github.com/JuIvyy/GPOcc。
英文原文摘要 1588 字符
Accurate 3D scene understanding is essential for embodied intelligence, with occupancy prediction emerging as a key task for reasoning about both objects and free space. Existing approaches largely rely on depth priors (e.g., DepthAnything) but make only limited use of 3D cues, restricting performance and generalization. Recently, visual geometry models such as VGGT have shown strong capability in providing rich 3D priors, but similar to monocular depth foundation models, they still operate at the level of visible surfaces rather than volumetric interiors, motivating us to explore how to more effectively leverage these increasingly powerful geometry priors for 3D occupancy prediction. We present GPOcc, a framework that leverages generalizable visual geometry priors (GPs) for monocular occupancy prediction. Our method extends surface points inward along camera rays to generate volumetric samples, which are represented as Gaussian primitives for probabilistic occupancy inference. To handle streaming input, we further design a training-free incremental update strategy that fuses per-frame Gaussians into a unified global representation. Experiments on Occ-ScanNet and EmbodiedOcc-ScanNet demonstrate significant gains: GPOcc improves mIoU by +9.99 in the monocular setting and +11.79 in the streaming setting over prior state of the art. Under the same depth prior, it achieves +6.73 mIoU while running 2.65 times faster. These results highlight that GPOcc leverages geometry priors more effectively and efficiently. Code will be released at https://github.com/JuIvyy/GPOcc.