SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Jin, Zhao, Tu, Rong-Cheng, Liao, Jingyi, Sun, Wenhao, Luo, Xiao, Liu, Shunyu, Tao, Dacheng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915361361756160
author Jin, Zhao
Tu, Rong-Cheng
Liao, Jingyi
Sun, Wenhao
Luo, Xiao
Liu, Shunyu
Tao, Dacheng
author_facet Jin, Zhao
Tu, Rong-Cheng
Liao, Jingyi
Sun, Wenhao
Luo, Xiao
Liu, Shunyu
Tao, Dacheng
contents 3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies have explored zero-shot 3DVG by leveraging the extensive knowledge and powerful reasoning capabilities of pre-trained LLMs and VLMs. However, existing paradigms tend to emphasize either spatial (3D-based) or semantic (2D-based) understanding, limiting their effectiveness in complex real-world applications. In this work, we introduce SPAZER - a VLM-driven agent that combines both modalities in a progressive reasoning framework. It first holistically analyzes the scene and produces a 3D rendering from the optimal viewpoint. Based on this, anchor-guided candidate screening is conducted to perform a coarse-level localization of potential objects. Furthermore, leveraging retrieved relevant 2D camera images, 3D-2D joint decision-making is efficiently performed to determine the best-matching object. By bridging spatial and semantic reasoning neural streams, SPAZER achieves robust zero-shot grounding without training on 3D-labeled data. Extensive experiments on ScanRefer and Nr3D benchmarks demonstrate that SPAZER significantly outperforms previous state-of-the-art zero-shot methods, achieving notable gains of 9.0% and 10.9% in accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding
Jin, Zhao
Tu, Rong-Cheng
Liao, Jingyi
Sun, Wenhao
Luo, Xiao
Liu, Shunyu
Tao, Dacheng
Computer Vision and Pattern Recognition
3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies have explored zero-shot 3DVG by leveraging the extensive knowledge and powerful reasoning capabilities of pre-trained LLMs and VLMs. However, existing paradigms tend to emphasize either spatial (3D-based) or semantic (2D-based) understanding, limiting their effectiveness in complex real-world applications. In this work, we introduce SPAZER - a VLM-driven agent that combines both modalities in a progressive reasoning framework. It first holistically analyzes the scene and produces a 3D rendering from the optimal viewpoint. Based on this, anchor-guided candidate screening is conducted to perform a coarse-level localization of potential objects. Furthermore, leveraging retrieved relevant 2D camera images, 3D-2D joint decision-making is efficiently performed to determine the best-matching object. By bridging spatial and semantic reasoning neural streams, SPAZER achieves robust zero-shot grounding without training on 3D-labeled data. Extensive experiments on ScanRefer and Nr3D benchmarks demonstrate that SPAZER significantly outperforms previous state-of-the-art zero-shot methods, achieving notable gains of 9.0% and 10.9% in accuracy.
title SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.21924