Object2Scene：将物体置于上下文以实现开放词汇3D检测
Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detection
AI总结：
本文提出Object2Scene，通过将大规模3D物体数据集中的物体插入现有3D场景并生成文本描述来增强开放词汇3D检测，同时提出统一检测与视觉定位的L3Det框架和跨域对比学习方法，在多个基准上取得优越性能。
摘要：
基于点云的开放词汇3D物体检测旨在检测训练集中没有真值标注的3D类别。由于3D场景的数据和标注（带有类别标签或文本描述的边界框）有限，这一任务极具挑战性。以往方法利用大规模、丰富标注的图像数据集作为3D与类别语义之间的桥梁，但需要在2D图像和3D点之间进行额外的对齐过程，限制了3D检测器的开放词汇能力。我们不利用2D图像，而是提出Object2Scene，这是第一种利用大规模、大词汇量3D物体数据集来增强现有3D场景数据集以进行开放词汇3D物体检测的方法。Object2Scene将来自不同来源的物体插入3D场景中，以丰富3D场景数据集的词汇量，并为新插入的物体生成文本描述。我们进一步引入了一个统一3D检测和视觉定位的框架，名为L3Det，并提出了一种跨域类别级对比学习方法，以缓解来自不同数据集的3D物体之间的域差距。在现有开放词汇3D物体检测基准上的大量实验表明，Object2Scene获得了优于现有方法的性能。我们进一步在一个新的基准OV-ScanNet-200上验证了Object2Scene的有效性，将所有稀有类别作为训练期间未见的新类别保留。
英文摘要：
Point cloud-based open-vocabulary 3D object detection aims to detect 3D categories that do not have ground-truth annotations in the training set. It is extremely challenging because of the limited data and annotations (bounding boxes with class labels or text descriptions) of 3D scenes. Previous approaches leverage large-scale richly-annotated image datasets as a bridge between 3D and category semantics but require an extra alignment process between 2D images and 3D points, limiting the open-vocabulary ability of 3D detectors. Instead of leveraging 2D images, we propose Object2Scene, the first approach that leverages large-scale large-vocabulary 3D object datasets to augment existing 3D scene datasets for open-vocabulary 3D object detection. Object2Scene inserts objects from different sources into 3D scenes to enrich the vocabulary of 3D scene datasets and generates text descriptions for the newly inserted objects. We further introduce a framework that unifies 3D detection and visual grounding, named L3Det, and propose a cross-domain category-level contrastive learning approach to mitigate the domain gap between 3D objects from different datasets. Extensive experiments on existing open-vocabulary 3D object detection benchmarks show that Object2Scene obtains superior performance over existing methods. We further verify the effectiveness of Object2Scene on a new benchmark OV-ScanNet-200, by holding out all rare categories as novel categories not seen during training.
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。
