发表机构
The Hong Kong Polytechnic University; Eastern Institute of Technology; Shanghai Jiao Tong University; Wuhan University; The University of Hong Kong; Georgia Institute of Technology（香港理工大学; 东部理工学院; 上海交通大学; 武汉大学; 香港大学; 佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对现有室内占用基准和方法对长距离语义映射探索不足的问题，提出GEM-Occ框架，将局部视觉几何预测转化为语义高斯占用证据等并融合到持久分层记忆中，实验证明该框架在多方面优于现有基线。
AI 中文摘要
语义占用通过联合表示占用区域、观察到的自由空间、未知区域和对象语义，为具身室内智能体提供结构化空间记忆。然而，现有的室内占用基准和方法主要集中在单视图预测或房间级在线感知，对跨连接室内空间的长距离语义映射探索不足。我们引入了HIOcc，这是一个分层室内占用基准，它在保留ScanNet、ScanNet++和Matterport3D原生观察几何的同时，将它们统一在一个通用的稀疏语义占用格式下。HIOcc支持三种互补的评估模式。我们还提出了GEM-Occ，一种用于语义占用映射的高斯证据记忆框架。实验表明，GEM-Occ在局部占用预测、在线地图稳定性、自由空间推理、重访一致性和建筑级可扩展性方面优于现有方法。
英文摘要
Embodied agents exploring indoor environments require reliable semantic occupancy memory that persists across observations and revisits. Building such memory is challenging because each observation provides incomplete and uncertain geometric and semantic evidence. We introduce GEM-Occ, a Gaussian Evidence Memory framework that consolidates evidence accumulated over time into persistent semantic occupancy memory. Local predictions are converted into occupied semantic Gaussians and free-space ray evidence. Confidence- and visibility-aware causal updates integrate supporting observations, suppress occupancy contradicted by observed free space, and preserve previously observed structures through occlusion. A hierarchical memory organization supports continued mapping and efficient queries across connected indoor spaces. To evaluate this capability, we introduce HIOcc, a unified benchmark for embodied semantic occupancy memory. HIOcc establishes a shared semantic label space and evaluation framework spanning local prediction, room-level online mapping, and building-level mapping, while accommodating perspective and panoramic observations. Experiments on HIOcc demonstrate that GEM-Occ outperforms existing methods, enabling accurate semantic occupancy prediction and consistent online mapping across spatial scales with efficient memory usage and fast occupancy queries.
CommentsProject page: https://zhuhu00.top/GEM-Occ/
