Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiang, Xinhao, Peng, Kuan-Chuan, Lohit, Suhas, Jones, Michael J., Zhang, Jiawei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912551216873472
author Xiang, Xinhao
Peng, Kuan-Chuan
Lohit, Suhas
Jones, Michael J.
Zhang, Jiawei
author_facet Xiang, Xinhao
Peng, Kuan-Chuan
Lohit, Suhas
Jones, Michael J.
Zhang, Jiawei
contents 3D object detection plays a crucial role in autonomous systems, yet existing methods are limited by closed-set assumptions and struggle to recognize novel objects and their attributes in real-world scenarios. We propose OVODA, a novel framework enabling both open-vocabulary 3D object and attribute detection with no need to know the novel class anchor size. OVODA uses foundation models to bridge the semantic gap between 3D features and texts while jointly detecting attributes, e.g., spatial relationships, motion states, etc. To facilitate such research direction, we propose OVAD, a new dataset that supplements existing 3D object detection benchmarks with comprehensive attribute annotations. OVODA incorporates several key innovations, including foundation model feature concatenation, prompt tuning strategies, and specialized techniques for attribute detection, including perspective-specified prompts and horizontal flip augmentation. Our results on both the nuScenes and Argoverse 2 datasets show that under the condition of no given anchor sizes of novel classes, OVODA outperforms the state-of-the-art methods in open-vocabulary 3D object detection while successfully recognizing object attributes. Our OVAD dataset is released here: https://doi.org/10.5281/zenodo.16904069 .
format Preprint
id arxiv_https___arxiv_org_abs_2508_16812
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes
Xiang, Xinhao
Peng, Kuan-Chuan
Lohit, Suhas
Jones, Michael J.
Zhang, Jiawei
Computer Vision and Pattern Recognition
3D object detection plays a crucial role in autonomous systems, yet existing methods are limited by closed-set assumptions and struggle to recognize novel objects and their attributes in real-world scenarios. We propose OVODA, a novel framework enabling both open-vocabulary 3D object and attribute detection with no need to know the novel class anchor size. OVODA uses foundation models to bridge the semantic gap between 3D features and texts while jointly detecting attributes, e.g., spatial relationships, motion states, etc. To facilitate such research direction, we propose OVAD, a new dataset that supplements existing 3D object detection benchmarks with comprehensive attribute annotations. OVODA incorporates several key innovations, including foundation model feature concatenation, prompt tuning strategies, and specialized techniques for attribute detection, including perspective-specified prompts and horizontal flip augmentation. Our results on both the nuScenes and Argoverse 2 datasets show that under the condition of no given anchor sizes of novel classes, OVODA outperforms the state-of-the-art methods in open-vocabulary 3D object detection while successfully recognizing object attributes. Our OVAD dataset is released here: https://doi.org/10.5281/zenodo.16904069 .
title Towards Open-Vocabulary Multimodal 3D Object Detection with Attributes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.16812