Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Dai, Shaohui, Qu, Yansong, Li, Zheyan, Li, Xinyang, Zhang, Shengchuan, Cao, Liujuan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915248813899776
author Dai, Shaohui
Qu, Yansong
Li, Zheyan
Li, Xinyang
Zhang, Shengchuan
Cao, Liujuan
author_facet Dai, Shaohui
Qu, Yansong
Li, Zheyan
Li, Xinyang
Zhang, Shengchuan
Cao, Liujuan
contents Bridging natural language and 3D geometry is a crucial step toward flexible, language-driven scene understanding. While recent advances in 3D Gaussian Splatting (3DGS) have enabled fast and high-quality scene reconstruction, research has also explored incorporating open-vocabulary understanding into 3DGS. However, most existing methods require iterative optimization over per-view 2D semantic feature maps, which not only results in inefficiencies but also leads to inconsistent 3D semantics across views. To address these limitations, we introduce a training-free framework that constructs a superpoint graph directly from Gaussian primitives. The superpoint graph partitions the scene into spatially compact and semantically coherent regions, forming view-consistent 3D entities and providing a structured foundation for open-vocabulary understanding. Based on the graph structure, we design an efficient reprojection strategy that lifts 2D semantic features onto the superpoints, avoiding costly multi-view iterative training. The resulting representation ensures strong 3D semantic coherence and naturally supports hierarchical understanding, enabling both coarse- and fine-grained open-vocabulary perception within a unified semantic field. Extensive experiments demonstrate that our method achieves state-of-the-art open-vocabulary segmentation performance, with semantic field reconstruction completed over $30\times$ faster. Our code will be available at https://github.com/Atrovast/THGS.
format Preprint
id arxiv_https___arxiv_org_abs_2504_13153
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs
Dai, Shaohui
Qu, Yansong
Li, Zheyan
Li, Xinyang
Zhang, Shengchuan
Cao, Liujuan
Computer Vision and Pattern Recognition
Bridging natural language and 3D geometry is a crucial step toward flexible, language-driven scene understanding. While recent advances in 3D Gaussian Splatting (3DGS) have enabled fast and high-quality scene reconstruction, research has also explored incorporating open-vocabulary understanding into 3DGS. However, most existing methods require iterative optimization over per-view 2D semantic feature maps, which not only results in inefficiencies but also leads to inconsistent 3D semantics across views. To address these limitations, we introduce a training-free framework that constructs a superpoint graph directly from Gaussian primitives. The superpoint graph partitions the scene into spatially compact and semantically coherent regions, forming view-consistent 3D entities and providing a structured foundation for open-vocabulary understanding. Based on the graph structure, we design an efficient reprojection strategy that lifts 2D semantic features onto the superpoints, avoiding costly multi-view iterative training. The resulting representation ensures strong 3D semantic coherence and naturally supports hierarchical understanding, enabling both coarse- and fine-grained open-vocabulary perception within a unified semantic field. Extensive experiments demonstrate that our method achieves state-of-the-art open-vocabulary segmentation performance, with semantic field reconstruction completed over $30\times$ faster. Our code will be available at https://github.com/Atrovast/THGS.
title Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.13153