工业环境中的开放词汇3D场景感知
Open-vocabulary 3D scene perception in industrial environments
AI总结：
本研究提出了一种无需训练的开放词汇3D感知流程，通过合并预计算超点生成掩码，提升工业环境中的3D场景感知能力。
摘要：
在生产、物流或制造环境中实现自主视觉应用需要超越少量固定类别的感知能力。最近的开放词汇方法利用2D视觉-语言基础模型（VLFMs）来解决这一任务，但通常依赖于在非工业数据集（如家庭场景）上预训练的类无关分割模型。在本工作中，我们首先证明此类模型无法泛化，对常见工业物体表现不佳。因此，我们提出了一种无需训练的开放词汇3D感知流程，以克服这一限制。代替使用预训练模型生成实例提案，我们的方法只是通过合并基于语义特征的预计算超点来生成掩码。随后，我们在具有代表性的3D工业车间场景上评估域适应的VLFM
英文摘要：
Autonomous vision applications in production, intralogistics, or manufacturing environments require perception capabilities beyond a small, fixed set of classes. Recent open-vocabulary methods, leveraging 2D Vision-Language Foundation Models (VLFMs), target this task but often rely on class-agnostic segmentation models pre-trained on non-industrial datasets (e.g., household scenes). In this work, we first demonstrate that such models fail to generalize, performing poorly on common industrial objects. Therefore, we propose a training-free, open-vocabulary 3D perception pipeline that overcomes this limitation. Instead of using a pre-trained model to generate instance proposals, our method simply generates masks by merging pre-computed superpoints based on their semantic features. Following, we evaluate the domain-adapted VLFM "IndustrialCLIP" on a representative 3D industrial workshop scene for open-vocabulary querying. Our qualitative results demonstrate successful segmentation of industrial objects.
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。
