OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields

TL;DR

OpenHype introduces a hyperbolic embedding approach for hierarchical scene modeling in neural radiance fields, enabling efficient, continuous, and multi-scale 3D scene understanding without predefined hierarchies.

Contribution

It is the first to utilize hyperbolic geometry for implicit hierarchical scene representations in radiance fields, improving flexibility and efficiency.

Findings

Outperforms state-of-the-art methods on standard benchmarks.

Enables smooth hierarchy traversal via geodesic paths.

Achieves better efficiency and adaptability in 3D scene understanding.

Abstract

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.