OG：为视觉占据预测配备实例分割与视觉定位能力
OG: Equip vision occupancy with instance segmentation and visual grounding
AI总结：
针对占据预测缺少实例区分且无法进行视觉定位的问题，本文提出 OG，利用亲和场聚类和 2D-3D 实例关联，结合 grounded-SAM 实现体素级实例分割与视觉定位。
摘要：
占据预测任务专注于推断每个体素的几何结构和语义标签，是一项重要的感知任务。然而，它仍然只是一个语义分割任务，无法区分不同的实例。此外，尽管 Open-Vocabulary Occupancy（OVO）等现有工作已经解决了开放词汇检测问题，但据我们所知，占据场景中的视觉定位问题尚未得到解决。为克服上述两个局限，本文提出 Occupancy Grounding（OG）这一新方法：它为普通占据预测赋予实例分割能力，并借助 grounded-SAM 以体素方式执行视觉定位。该方法的关键在于：（1）用于实例聚类的亲和场预测；（2）用于对齐二维实例掩码与三维占据实例的关联策略。本文开展了大量实验，并在下文展示可视化结果与分析。代码将很快公开发布。
英文摘要：
Occupancy prediction tasks focus on the inference of both geometry and semantic labels for each voxel, which is an important perception mission. However, it is still a semantic segmentation task without distinguishing various instances. Further, although some existing works, such as Open-Vocabulary Occupancy (OVO), have already solved the problem of open vocabulary detection, visual grounding in occupancy has not been solved to the best of our knowledge. To tackle the above two limitations, this paper proposes Occupancy Grounding (OG), a novel method that equips vanilla occupancy instance segmentation ability and could operate visual grounding in a voxel manner with the help of grounded-SAM. Keys to our approach are (1) affinity field prediction for instance clustering and (2) association strategy for aligning 2D instance masks and 3D occupancy instances. Extensive experiments have been conducted whose visualization results and analysis are shown below. Our code will be publicly released soon.
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。
