Home | Publications | LNW+26a

SING3R-SLAM: Submap-Based Indoor Monocular Gaussian SLAM With 3D Reconstruction Priors

MCML Authors

Abstract

Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semantic predictions across multi-view observations. In this paper, we present OpenGaFF, a novel framework for open-vocabulary 3D scene understanding built upon 3D Gaussian Splatting. At the core of our method is a Gaussian Feature Field that models semantics as a continuous function of Gaussian geometry and appearance. By explicitly conditioning semantic predictions on geometric structure, this formulation strengthens the coupling between geometry and semantics, leading to improved spatial coherence across similar structures in 3D space. To further enforce object-level semantic consistency, we introduce a structured codebook that serves as a set of shared semantic primitives. Furthermore, a codebook-guided attention mechanism is proposed to retrieve language features via similarity matching between query embeddings and learned codebook entries, enabling robust open-vocabulary reasoning while reducing intra-object feature variance. Extensive experiments on standard 2D and 3D open-vocabulary benchmarks demonstrate that our method consistently outperforms prior approaches, achieving improved segmentation quality, stronger 3D semantic consistency and a semantically interpretable codebook that provides insight into the learned representation.

article LNW+26a

IEEE Robotics and Automation Letters

Early Access. Sep. 2026.
Top Journal

Authors

K. Li • M. Niemeyer • S. Wang • S. Gasperini • N. Navab • F. Tombari

Links

DOI

In Collaboration

 Google
 VisualAIs Labs

Research Area

 C1 | Medicine

BibTeXKey: LNW+26a

#p-navab #p-tombari
Back to Top