OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields
This addresses the problem of inefficient and poorly generalizing hierarchical modeling in 3D scene understanding for autonomous agents, representing an incremental improvement over existing methods.
The paper tackled the challenge of modeling hierarchical structures in 3D scenes using implicit representations like Neural Radiance Fields, which was previously unexplored, and proposed OpenHype, a method that uses hyperbolic embeddings to achieve this, resulting in superior efficiency and adaptability on standard benchmarks.
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.