AutoOcc：基于视觉-语言引导的高斯泼溅的自动开放式语义占据标注
AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting
AI总结：
AutoOcc提出一种基于视觉-语言模型引导的高斯泼溅的自动化流水线，用于开放式语义占据标注，无需人工标签，在静态和动态场景中均表现稳健。
摘要：
从原始传感器数据中获取高质量的3D语义占据仍然是一项重要但具有挑战性的任务，通常需要大量的人工标注。在这项工作中，我们提出了AutoOcc，一个以视觉为中心的自动化流水线，用于开放式语义占据标注，该流水线集成了由视觉-语言模型引导的可微高斯泼溅。我们将开放式语义3D占据重建任务公式化，通过结合视觉-语言模型和基础视觉模型的注意力图来自动生成场景占据。我们设计了语义感知的高斯作为中间几何描述符，并提出了一种累积的高斯到体素泼溅算法，该算法能够实现有效且高效的占据标注。我们的框架在无需人工标签的情况下优于现有的自动占据标注方法。AutoOcc还支持开放式语义占据自动标注，在静态和动态复杂场景中均实现了稳健的性能。
英文摘要：
Obtaining high-quality 3D semantic occupancy from raw sensor data remains an essential yet challenging task, often requiring extensive manual labeling. In this work, we propose AutoOcc, a vision-centric automated pipeline for open-ended semantic occupancy annotation that integrates differentiable Gaussian splatting guided by vision-language models. We formulate the open-ended semantic 3D occupancy reconstruction task to automatically generate scene occupancy by combining attention maps from vision-language models and foundation vision models. We devise semantic-aware Gaussians as intermediate geometric descriptors and propose a cumulative Gaussian-to-voxel splatting algorithm that enables effective and efficient occupancy annotation. Our framework outperforms existing automated occupancy annotation methods without human labels. AutoOcc also enables open-ended semantic occupancy auto-labeling, achieving robust performance in both static and dynamically complex scenarios.
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。
