用双曲空间建模3D场景层次结构，提升理解效率与泛化能力
OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields
- 采用连续双曲潜空间表示层级关系，支持多尺度嵌入
- 单次渲染完成不同粒度的结构捕捉，推理速度更快
- 适用于开放词汇场景，适合自主代理的复杂环境理解
建模3D物体与场景的固有层次结构对自主代理理解环境至关重要。然而，使用隐式表示（如神经辐射场）实现这一目标仍是未解难题。现有显式建模方法通常存在显著局限：要么需要多次渲染才能获取不同粒度的嵌入，大幅增加推理时间；要么依赖预定义的封闭集离散层次，难以泛化到真实世界中多样且细微的结构。为此，我们提出OpenHype，一种基于连续双曲潜空间表示场景层次的新方法。利用双曲几何特性，OpenHype自然编码多尺度关系，并可通过潜空间中的测地线路径实现层次平滑遍历。该方法在标准基准上超越现有最优方法，展现出更优的效率与适应性。
原文摘要 · Abstract (English)
Modeling the inherent hierarchical structure of 3D objects and 3D scenes is highly desirable, as it enables a more holistic understanding of environments for autonomous agents. Accomplishing this with implicit representations, such as Neural Radiance Fields, remains an unexplored challenge. Existing methods that explicitly model hierarchical structures often face significant limitations: they either require multiple rendering passes to capture embeddings at different levels of granularity, significantly increasing inference time, or rely on predefined, closed-set discrete hierarchies that generalize poorly to the diverse and nuanced structures encountered by agents in the real world. To address these challenges, we propose OpenHype, a novel approach that represents scene hierarchies using a continuous hyperbolic latent space. By leveraging the properties of hyperbolic geometry, OpenHype naturally encodes multi-scale relationships and enables smooth traversal of hierarchies through geodesic paths in latent space. Our method outperforms state-of-the-art approaches on standard benchmarks, demonstrating superior efficiency and adaptability in 3D scene understanding.
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。