单目开放词汇占用预测用于室内场景
Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes
AI总结：
该研究提出了一种基于几何的监督方法，用于单目开放词汇室内场景的占用预测，通过引入一种基于Poisson的透明度感知方法和逐步温度衰减调度，提高了几何和语义对齐的稳定性与精度，实验结果显示在Occ-ScanNet数据集上取得了较高的IoU和mIoU指标。
摘要：
开放词汇3D占用对于具有体素的智能体至关重要，这些智能体需要理解具有丰富语义类别的复杂室内环境，并超越固定分类体系。尽管最近的研究在户外驾驶场景中探索了开放词汇占用，但这些方法在室内场景中表现不佳，因为几何更密集，布局更复杂，语义更细粒度。为了解决这些挑战，我们采用仅使用二元占用标签（占用vs自由）的几何-only监督范式。我们的框架基于3D语言嵌入高斯，这些高斯作为统一的中间表示，将细粒度3D几何与语言对齐的语义嵌入耦合在一起。在几何方面，我们发现现有高斯到占用运算符在如此弱的监督下无法收敛，我们引入了一种基于Poisson的透明度感知方法，稳定了体积分组。在语义方面，直接对渲染特征和开放词汇分割特征之间的对齐导致特征混合；因此，我们提出了一个逐步温度衰减调度，逐步在溅射过程中锐化透明度，加强高斯-语言对齐。在Occ-ScanNet上，我们的框架在开放词汇设置中实现了59.50 IoU和21.05 mIoU，超过了所有现有的占用方法在IoU，并在mIoU上大幅优于先前的开放词汇方法。代码将在https://github.com/JuIvyy/LegoOcc上发布。
英文摘要：
Open-vocabulary 3D occupancy is vital for embodied agents, which need to understand complex indoor environments where semantic categories are abundant and evolve beyond fixed taxonomies. While recent work has explored open-vocabulary occupancy in outdoor driving scenarios, such methods transfer poorly indoors, where geometry is denser, layouts are more intricate, and semantics are far more fine-grained. To address these challenges, we adopt a geometry-only supervision paradigm that uses only binary occupancy labels (occupied vs free). Our framework builds upon 3D Language-Embedded Gaussians, which serve as a unified intermediate representation coupling fine-grained 3D geometry with a language-aligned semantic embedding. On the geometry side, we find that existing Gaussian-to-Occupancy operators fail to converge under such weak supervision, and we introduce an opacity-aware, Poisson-based approach that stabilizes volumetric aggregation. On the semantic side, direct alignment between rendered features and open-vocabulary segmentation features suffers from feature mixing; we therefore propose a Progressive Temperature Decay schedule that gradually sharpens opacities during splatting, strengthening Gaussian-language alignment. On Occ-ScanNet, our framework achieves 59.50 IoU and 21.05 mIoU in the open-vocabulary setting, surpassing all existing occupancy methods in IoU and outperforming prior open-vocabulary approaches by a large margin in mIoU. Code will be released at https://github.com/JuIvyy/LegoOcc.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
