In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks. However, when extended to point cloud data, existing works mainly focus on building task-specific models, and fail to extract universal 3D vision-language embedding that generalize well. We carefully investigate three common tasks in semantic 3D scene understanding, and derive key insights into the development of a pre-training model. Motivated by these observations, we propose a vision-language pre-training framework 3DVLP (3D vision-language pre-training with object contrastive learning), which transfers flexibly on 3D vision-language downstream tasks. 3DVLP takes visual grounding as the proxy task and introduces Object-level IoU-guided Detection (OID) loss to obtain high-quality proposals in the scene. Moreover, we design Object-level Cross-Contrastive alignment (OCC) task and Object-level Self-Contrastive learning (OSC) task to align the objects with descriptions and distinguish different objects in the scene, respectively. Extensive experiments verify the excellent performance of 3DVLP on three 3D vision-language tasks, reflecting its superiority in semantic 3D scene understanding.

翻译：近年来，视觉-语言预训练框架在自然语言处理和计算机视觉领域取得了显著进展，在各种下游任务上实现了性能的大幅提升。然而，当扩展到点云数据时，现有工作主要致力于构建任务特定模型，未能提取出泛化能力良好的通用3D视觉-语言嵌入。我们仔细研究了语义3D场景理解中的三个常见任务，并得出了预训练模型开发的关键见解。受这些观察的启发，我们提出了一种视觉-语言预训练框架3DVLP（基于目标对比学习的3D视觉-语言预训练），能够灵活迁移至3D视觉-语言下游任务。3DVLP以视觉定位作为代理任务，引入目标级IoU引导检测（OID）损失，以在场景中获取高质量候选区域。此外，我们设计了目标级跨模态对比对齐（OCC）任务和目标级自对比学习（OSC）任务，分别用于对齐目标与描述文本，以及区分场景中的不同目标。大量实验验证了3DVLP在三个3D视觉-语言任务上的优异性能，体现了其在语义3D场景理解中的优越性。