论文标题
待办事项：用于理解3D桌面场景的大型数据集
TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes
论文作者
论文摘要
许多基本的室内活动，例如饮食或写作，总是在不同的桌面上（例如咖啡桌，写桌）进行。在3D室内场景解析应用程序中了解桌面场景是必不可少的。不幸的是，由于3D桌面场景在当前数据集中很少可用，因此很难通过直接部署数据驱动算法来满足这一需求。为了解决此缺陷，我们介绍了To-Scene，这是一个专注于桌面场景的大规模数据集，其中包含20,740个带有三个变体的场景。为了获取数据，我们设计了一个高效且可扩展的框架，其中开发了众包UI将CAD对象从扫描室传递到桌面上，然后将输出桌面场景模拟为真实的扫描并自动带注释。 此外，提出了一种桌面吸引的学习策略，以更好地感知小型桌面实例。值得注意的是，我们还提供了真正的扫描测试集，以验证待机的实际价值。实验表明，经过训练的to-Scene的算法确实在现实的测试数据上工作，而我们提出的桌面感知学习策略大大改善了3D语义细分和对象检测任务的最新结果。数据集和代码可在https://github.com/gap-lab-cuhk-sz/to-scene上找到。
Many basic indoor activities such as eating or writing are always conducted upon different tabletops (e.g., coffee tables, writing desks). It is indispensable to understanding tabletop scenes in 3D indoor scene parsing applications. Unfortunately, it is hard to meet this demand by directly deploying data-driven algorithms, since 3D tabletop scenes are rarely available in current datasets. To remedy this defect, we introduce TO-Scene, a large-scale dataset focusing on tabletop scenes, which contains 20,740 scenes with three variants. To acquire the data, we design an efficient and scalable framework, where a crowdsourcing UI is developed to transfer CAD objects from ModelNet and ShapeNet onto tables from ScanNet, then the output tabletop scenes are simulated into real scans and annotated automatically. Further, a tabletop-aware learning strategy is proposed for better perceiving the small-sized tabletop instances. Notably, we also provide a real scanned test set TO-Real to verify the practical value of TO-Scene. Experiments show that the algorithms trained on TO-Scene indeed work on the realistic test data, and our proposed tabletop-aware learning strategy greatly improves the state-of-the-art results on both 3D semantic segmentation and object detection tasks. Dataset and code are available at https://github.com/GAP-LAB-CUHK-SZ/TO-Scene.
