ExtrinSplat: Decoupling Geometry and Semantics for Open-Vocabulary Understanding in 3D Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ding, Jiayu, Liu, Xinpeng, Pan, Zhiyi, Long, Shiqiang, Li, Ge
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918412035293184
author Ding, Jiayu
Liu, Xinpeng
Pan, Zhiyi
Long, Shiqiang
Li, Ge
author_facet Ding, Jiayu
Liu, Xinpeng
Pan, Zhiyi
Long, Shiqiang
Li, Ge
contents Lifting 2D open-vocabulary understanding into 3D Gaussian Splatting (3DGS) scenes is a critical challenge. Mainstream methods, built on an embedding paradigm, suffer from three key flaws: (i) geometry-semantic inconsistency, where points, rather than objects, serve as the semantic basis, limiting semantic fidelity; (ii) semantic bloat from injecting gigabytes of feature data into the geometry; and (iii) semantic rigidity, as one feature per Gaussian struggles to capture rich polysemy. To overcome these limitations, we introduce ExtrinSplat, a framework built on the extrinsic paradigm that decouples geometry from semantics. Instead of embedding features, ExtrinSplat clusters Gaussians into multi-granularity, overlapping 3D object groups. A Vision-Language Model (VLM) then interprets these groups to generate lightweight textual hypotheses, creating an extrinsic index layer that natively supports complex polysemy. By replacing costly feature embedding with lightweight indices, ExtrinSplat reduces scene adaptation time from hours to minutes and lowers storage overhead by several orders of magnitude. On benchmark tasks for open-vocabulary 3D object selection and semantic segmentation, ExtrinSplat outperforms established embedding-based frameworks, validating the efficacy and efficiency of the proposed extrinsic paradigm.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22225
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ExtrinSplat: Decoupling Geometry and Semantics for Open-Vocabulary Understanding in 3D Gaussian Splatting
Ding, Jiayu
Liu, Xinpeng
Pan, Zhiyi
Long, Shiqiang
Li, Ge
Computer Vision and Pattern Recognition
Artificial Intelligence
Lifting 2D open-vocabulary understanding into 3D Gaussian Splatting (3DGS) scenes is a critical challenge. Mainstream methods, built on an embedding paradigm, suffer from three key flaws: (i) geometry-semantic inconsistency, where points, rather than objects, serve as the semantic basis, limiting semantic fidelity; (ii) semantic bloat from injecting gigabytes of feature data into the geometry; and (iii) semantic rigidity, as one feature per Gaussian struggles to capture rich polysemy. To overcome these limitations, we introduce ExtrinSplat, a framework built on the extrinsic paradigm that decouples geometry from semantics. Instead of embedding features, ExtrinSplat clusters Gaussians into multi-granularity, overlapping 3D object groups. A Vision-Language Model (VLM) then interprets these groups to generate lightweight textual hypotheses, creating an extrinsic index layer that natively supports complex polysemy. By replacing costly feature embedding with lightweight indices, ExtrinSplat reduces scene adaptation time from hours to minutes and lowers storage overhead by several orders of magnitude. On benchmark tasks for open-vocabulary 3D object selection and semantic segmentation, ExtrinSplat outperforms established embedding-based frameworks, validating the efficacy and efficiency of the proposed extrinsic paradigm.
title ExtrinSplat: Decoupling Geometry and Semantics for Open-Vocabulary Understanding in 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.22225