构建高精度合成场景图数据集，引入参数化与原型关系新概念。
CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations
- 提出参数化与原型关系，细化物体间关系描述
- 构建包含所有物体关系的高精度合成数据集
- 提升下游任务中的推理与规划能力，适合场景理解研究者
二维场景图为场景理解提供了结构化且可解释的框架。然而，现有工作仍受限于高质量场景图数据的缺乏。为突破这一数据瓶颈，我们提出 CoPa-SG，一个具有高度精确真实标签和全面物体间关系标注的合成场景图数据集。此外，我们引入参数化关系和原型关系两个新基础概念：前者通过角度、距离等附加参数，实现比传统关系更细粒度的表示；后者编码场景中假设性关系，描述若新增物体时关系将如何形成。利用 CoPa-SG，我们对比了多种场景图生成模型的性能，并展示了如何将新关系类型集成到下游应用中，以增强规划与推理能力。
原文摘要 · Abstract (English)
2D scene graphs provide a structural and explainable framework for scene understanding. However, current work still struggles with the lack of accurate scene graph data. To overcome this data bottleneck, we present CoPa-SG, a synthetic scene graph dataset with highly precise ground truth and exhaustive relation annotations between all objects. Moreover, we introduce parametric and proto-relations, two new fundamental concepts for scene graphs. The former provides a much more fine-grained representation than its traditional counterpart by enriching relations with additional parameters such as angles or distances. The latter encodes hypothetical relations in a scene graph and describes how relations would form if new objects are placed in the scene. Using CoPa-SG, we compare the performance of various scene graph generation models. We demonstrate how our new relation types can be integrated in downstream applications to enhance planning and reasoning capabilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。