CVApr 11, 2025

FMLGS: Fast Multilevel Language Embedded Gaussians for Part-level Interactive Agents

arXiv:2504.08581v12 citationsh-index: 12
Originality Incremental advance
AI Analysis

This work addresses the challenge of ambiguous language queries for object parts in 3D applications like embodied AI, representing a strong domain-specific advancement.

The paper tackles the problem of multi-granularity interaction in 3D scenes by developing FMLGS, a method for part-level open-vocabulary querying within 3D Gaussian Splatting, which achieves state-of-the-art performance with 98× faster speed than LERF and top accuracy.

The semantically interactive radiance field has long been a promising backbone for 3D real-world applications, such as embodied AI to achieve scene understanding and manipulation. However, multi-granularity interaction remains a challenging task due to the ambiguity of language and degraded quality when it comes to queries upon object components. In this work, we present FMLGS, an approach that supports part-level open-vocabulary query within 3D Gaussian Splatting (3DGS). We propose an efficient pipeline for building and querying consistent object- and part-level semantics based on Segment Anything Model 2 (SAM2). We designed a semantic deviation strategy to solve the problem of language ambiguity among object parts, which interpolates the semantic features of fine-grained targets for enriched information. Once trained, we can query both objects and their describable parts using natural language. Comparisons with other state-of-the-art methods prove that our method can not only better locate specified part-level targets, but also achieve first-place performance concerning both speed and accuracy, where FMLGS is 98 x faster than LERF, 4 x faster than LangSplat and 2.5 x faster than LEGaussians. Meanwhile, we further integrate FMLGS as a virtual agent that can interactively navigate through 3D scenes, locate targets, and respond to user demands through a chat interface, which demonstrates the potential of our work to be further expanded and applied in the future.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes