Natural Language-Driven Viewpoint Navigation for Volume Exploration via Semantic Block Representation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhao, Xuan, Tao, Jun
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913982674108416
author Zhao, Xuan
Tao, Jun
author_facet Zhao, Xuan
Tao, Jun
contents Exploring volumetric data is crucial for interpreting scientific datasets. However, selecting optimal viewpoints for effective navigation can be challenging, particularly for users without extensive domain expertise or familiarity with 3D navigation. In this paper, we propose a novel framework that leverages natural language interaction to enhance volumetric data exploration. Our approach encodes volumetric blocks to capture and differentiate underlying structures. It further incorporates a CLIP Score mechanism, which provides semantic information to the blocks to guide navigation. The navigation is empowered by a reinforcement learning framework that leverage these semantic cues to efficiently search for and identify desired viewpoints that align with the user's intent. The selected viewpoints are evaluated using CLIP Score to ensure that they best reflect the user queries. By automating viewpoint selection, our method improves the efficiency of volumetric data navigation and enhances the interpretability of complex scientific phenomena.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06823
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Natural Language-Driven Viewpoint Navigation for Volume Exploration via Semantic Block Representation
Zhao, Xuan
Tao, Jun
Artificial Intelligence
Exploring volumetric data is crucial for interpreting scientific datasets. However, selecting optimal viewpoints for effective navigation can be challenging, particularly for users without extensive domain expertise or familiarity with 3D navigation. In this paper, we propose a novel framework that leverages natural language interaction to enhance volumetric data exploration. Our approach encodes volumetric blocks to capture and differentiate underlying structures. It further incorporates a CLIP Score mechanism, which provides semantic information to the blocks to guide navigation. The navigation is empowered by a reinforcement learning framework that leverage these semantic cues to efficiently search for and identify desired viewpoints that align with the user's intent. The selected viewpoints are evaluated using CLIP Score to ensure that they best reflect the user queries. By automating viewpoint selection, our method improves the efficiency of volumetric data navigation and enhances the interpretability of complex scientific phenomena.
title Natural Language-Driven Viewpoint Navigation for Volume Exploration via Semantic Block Representation
topic Artificial Intelligence
url https://arxiv.org/abs/2508.06823