ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Huang, Ronggang, Yang, Haoxin, Cai, Yan, Xu, Xuemiao, Zhang, Huaidong, He, Shengfeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911079123124224
author Huang, Ronggang
Yang, Haoxin
Cai, Yan
Xu, Xuemiao
Zhang, Huaidong
He, Shengfeng
author_facet Huang, Ronggang
Yang, Haoxin
Cai, Yan
Xu, Xuemiao
Zhang, Huaidong
He, Shengfeng
contents 3D visual grounding aims to identify and localize objects in a 3D space based on textual descriptions. However, existing methods struggle with disentangling targets from anchors in complex multi-anchor queries and resolving inconsistencies in spatial descriptions caused by perspective variations. To tackle these challenges, we propose ViewSRD, a framework that formulates 3D visual grounding as a structured multi-view decomposition process. First, the Simple Relation Decoupling (SRD) module restructures complex multi-anchor queries into a set of targeted single-anchor statements, generating a structured set of perspective-aware descriptions that clarify positional relationships. These decomposed representations serve as the foundation for the Multi-view Textual-Scene Interaction (Multi-TSI) module, which integrates textual and scene features across multiple viewpoints using shared, Cross-modal Consistent View Tokens (CCVTs) to preserve spatial correlations. Finally, a Textual-Scene Reasoning module synthesizes multi-view predictions into a unified and robust 3D visual grounding. Experiments on 3D visual grounding datasets show that ViewSRD significantly outperforms state-of-the-art methods, particularly in complex queries requiring precise spatial differentiation. Code is available at https://github.com/visualjason/ViewSRD.
format Preprint
id arxiv_https___arxiv_org_abs_2507_11261
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition
Huang, Ronggang
Yang, Haoxin
Cai, Yan
Xu, Xuemiao
Zhang, Huaidong
He, Shengfeng
Computer Vision and Pattern Recognition
3D visual grounding aims to identify and localize objects in a 3D space based on textual descriptions. However, existing methods struggle with disentangling targets from anchors in complex multi-anchor queries and resolving inconsistencies in spatial descriptions caused by perspective variations. To tackle these challenges, we propose ViewSRD, a framework that formulates 3D visual grounding as a structured multi-view decomposition process. First, the Simple Relation Decoupling (SRD) module restructures complex multi-anchor queries into a set of targeted single-anchor statements, generating a structured set of perspective-aware descriptions that clarify positional relationships. These decomposed representations serve as the foundation for the Multi-view Textual-Scene Interaction (Multi-TSI) module, which integrates textual and scene features across multiple viewpoints using shared, Cross-modal Consistent View Tokens (CCVTs) to preserve spatial correlations. Finally, a Textual-Scene Reasoning module synthesizes multi-view predictions into a unified and robust 3D visual grounding. Experiments on 3D visual grounding datasets show that ViewSRD significantly outperforms state-of-the-art methods, particularly in complex queries requiring precise spatial differentiation. Code is available at https://github.com/visualjason/ViewSRD.
title ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.11261