发表机构
The Hong Kong University of Science and Technology (Guangzhou); The Chinese University of Hong Kong, Shenzhen; Sun Yat-sen University; The Hong Kong Polytechnic University; Nanjing University of Aeronautics and Astronautics（香港科技大学（广州）; 香港中文大学（深圳）; 中山大学; 香港理工大学; 南京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对3D场景理解中从视觉观察恢复完整体积表示的挑战，提出GPOcc++，它基于视觉几何先验，将其转换为占用感知的稀疏高斯表示，能在统一框架中处理多视图观察和时间序列，扩展到室外，实验证明其性能强、效率高且泛化能力好。
AI 中文摘要
准确的3D场景理解对具身智能和自动驾驶至关重要，3D占用提供了对象、结构和自由空间的统一表示。然而，从视觉观察中恢复完整的体积表示仍具挑战性，尤其是在遮挡和未观察区域。视觉几何先验为应对这一挑战提供了强大且可推广的几何线索，但其输出以表面为中心，而占用预测需要对体积内部和自由空间进行推理。为弥合这一差距，我们引入了GPOcc，它将视觉几何先验转换为占用感知的稀疏高斯表示，以实现高效且富有表现力的体积场景建模。基于GPOcc，GPOcc++在统一框架中对多视图观察和时间序列进行建模，允许通过相同表示处理空间和时间证据。我们还将GPOcc++从室内场景扩展到室外占用预测。在室内和室外基准上的大量实验表明，在多视图和时间设置中均具有一致的强大性能，以及良好的效率和泛化能力。代码将在指定网址发布。
英文摘要
Accurate 3D scene understanding is fundamental to embodied intelligence and autonomous driving, where 3D occupancy provides a unified representation of objects, structures, and free space. However, recovering such a complete volumetric representation from visual observations remains challenging, particularly in occluded and unobserved regions. Visual geometry priors offer strong and generalizable geometric cues for addressing this challenge, but their outputs are inherently surface-centric, whereas occupancy prediction requires reasoning about volumetric interiors and free space. To bridge this gap, we introduce GPOcc, which transforms visual geometry priors into occupancy-aware sparse Gaussian representations for efficient and expressive volumetric scene modeling. Building on GPOcc, GPOcc++ models multi-view observations and temporal sequences within a unified framework, allowing spatial and temporal evidence to be handled through the same representation. We further extend GPOcc++ from indoor scenes to outdoor occupancy prediction. Extensive experiments on both indoor and outdoor benchmarks demonstrate consistently strong performance across both multi-view and temporal settings, together with favorable efficiency and generalization. Code will be released at https://github.com/JuIvyy/GPOcc.
