用双曲空间建模场景图，更好捕捉物体层次关系。
HSG: Hyperbolic Scene Graph
- 在双曲空间学习场景图嵌入，自然编码层级关系
- 图级别指标提升显著，最高图 IoU 达 33.51
- 适合需要结构一致性建模的多视角3D场景任务
场景图通过建模物体及其关系实现结构化视觉理解，广泛应用于多视角和3D场景推理。现有方法如 MSG 在欧几里得空间中使用对比学习和注意力关联学习场景图嵌入，但欧氏几何无法显式表达场所与物体间的层级蕴含关系，限制了表示的结构一致性。为此，我们提出双曲场景图（HSG），在双曲空间中学习场景图嵌入，利用几何距离自然编码层级关系。实验表明，HSG 在保持强检索性能的同时提升了层级结构质量。在图级别指标上表现最佳：HSG 达到 PP IoU 33.17，最高图 IoU 为 33.51，优于最佳 AoMSG 变体（25.37）8.14，验证了双曲表示学习在场景图建模中的有效性。代码已开源。
原文摘要 · Abstract (English)
Scene graph representations enable structured visual understanding by modeling objects and their relationships, and have been widely used for multiview and 3D scene reasoning. Existing methods such as MSG learn scene graph embeddings in Euclidean space using contrastive learning and attention based association. However, Euclidean geometry does not explicitly capture hierarchical entailment relationships between places and objects, limiting the structural consistency of learned representations. To address this, we propose Hyperbolic Scene Graph (HSG), which learns scene graph embeddings in hyperbolic space where hierarchical relationships are naturally encoded through geometric distance. Our results show that HSG improves hierarchical structure quality while maintaining strong retrieval performance. The largest gains are observed in graph level metrics: HSG achieves a PP IoU of 33.17 and the highest Graph IoU of 33.51, outperforming the best AoMSG variant (25.37) by 8.14, highlighting the effectiveness of hyperbolic representation learning for scene graph modeling. Code: https://github.com/AIGeeksGroup/HSG.
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。