Saved in:
Bibliographic Details
Main Authors: Xue, Jintang, Zhao, Ganning, Yao, Jie-En, Chen, Hong-En, Hu, Yue, Chen, Meida, You, Suya, Kuo, C. -C. Jay
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.14555
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909947002880000
author Xue, Jintang
Zhao, Ganning
Yao, Jie-En
Chen, Hong-En
Hu, Yue
Chen, Meida
You, Suya
Kuo, C. -C. Jay
author_facet Xue, Jintang
Zhao, Ganning
Yao, Jie-En
Chen, Hong-En
Hu, Yue
Chen, Meida
You, Suya
Kuo, C. -C. Jay
contents Understanding 3D scenes goes beyond simply recognizing objects; it requires reasoning about the spatial and semantic relationships between them. Current 3D scene-language models often struggle with this relational understanding, particularly when visual embeddings alone do not adequately convey the roles and interactions of objects. In this paper, we introduce Descrip3D, a novel and powerful framework that explicitly encodes the relationships between objects using natural language. Unlike previous methods that rely only on 2D and 3D embeddings, Descrip3D enhances each object with a textual description that captures both its intrinsic attributes and contextual relationships. These relational cues are incorporated into the model through a dual-level integration: embedding fusion and prompt-level injection. This allows for unified reasoning across various tasks such as grounding, captioning, and question answering, all without the need for task-specific heads or additional supervision. When evaluated on five benchmark datasets, including ScanRefer, Multi3DRefer, ScanQA, SQA3D, and Scan2Cap, Descrip3D consistently outperforms strong baseline models, demonstrating the effectiveness of language-guided relational representation for understanding complex indoor scenes. Our code and data are publicly available at https://github.com/jintangxue/Descrip3D.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14555
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions
Xue, Jintang
Zhao, Ganning
Yao, Jie-En
Chen, Hong-En
Hu, Yue
Chen, Meida
You, Suya
Kuo, C. -C. Jay
Computer Vision and Pattern Recognition
Understanding 3D scenes goes beyond simply recognizing objects; it requires reasoning about the spatial and semantic relationships between them. Current 3D scene-language models often struggle with this relational understanding, particularly when visual embeddings alone do not adequately convey the roles and interactions of objects. In this paper, we introduce Descrip3D, a novel and powerful framework that explicitly encodes the relationships between objects using natural language. Unlike previous methods that rely only on 2D and 3D embeddings, Descrip3D enhances each object with a textual description that captures both its intrinsic attributes and contextual relationships. These relational cues are incorporated into the model through a dual-level integration: embedding fusion and prompt-level injection. This allows for unified reasoning across various tasks such as grounding, captioning, and question answering, all without the need for task-specific heads or additional supervision. When evaluated on five benchmark datasets, including ScanRefer, Multi3DRefer, ScanQA, SQA3D, and Scan2Cap, Descrip3D consistently outperforms strong baseline models, demonstrating the effectiveness of language-guided relational representation for understanding complex indoor scenes. Our code and data are publicly available at https://github.com/jintangxue/Descrip3D.
title Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.14555