Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Haomeng, Yang, Chiao-An, Yeh, Raymond A.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.22306
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912162467807232
author Zhang, Haomeng
Yang, Chiao-An
Yeh, Raymond A.
author_facet Zhang, Haomeng
Yang, Chiao-An
Yeh, Raymond A.
contents Multi-object 3D Grounding involves locating 3D boxes based on a given query phrase from a point cloud. It is a challenging and significant task with numerous applications in visual understanding, human-computer interaction, and robotics. To tackle this challenge, we introduce D-LISA, a two-stage approach incorporating three innovations. First, a dynamic vision module that enables a variable and learnable number of box proposals. Second, a dynamic camera positioning that extracts features for each proposal. Third, a language-informed spatial attention module that better reasons over the proposals to output the final prediction. Empirically, experiments show that our method outperforms the state-of-the-art methods on multi-object 3D grounding by 12.8% (absolute) and is competitive in single-object 3D grounding.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22306
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention
Zhang, Haomeng
Yang, Chiao-An
Yeh, Raymond A.
Computer Vision and Pattern Recognition
Multi-object 3D Grounding involves locating 3D boxes based on a given query phrase from a point cloud. It is a challenging and significant task with numerous applications in visual understanding, human-computer interaction, and robotics. To tackle this challenge, we introduce D-LISA, a two-stage approach incorporating three innovations. First, a dynamic vision module that enables a variable and learnable number of box proposals. Second, a dynamic camera positioning that extracts features for each proposal. Third, a language-informed spatial attention module that better reasons over the proposals to output the final prediction. Empirically, experiments show that our method outperforms the state-of-the-art methods on multi-object 3D grounding by 12.8% (absolute) and is competitive in single-object 3D grounding.
title Multi-Object 3D Grounding with Dynamic Modules and Language-Informed Spatial Attention
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.22306