Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Huang, Kuan-Chih, Li, Xiangtai, Qi, Lu, Yan, Shuicheng, Yang, Ming-Hsuan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909484619661312
author Huang, Kuan-Chih
Li, Xiangtai
Qi, Lu
Yan, Shuicheng
Yang, Ming-Hsuan
author_facet Huang, Kuan-Chih
Li, Xiangtai
Qi, Lu
Yan, Shuicheng
Yang, Ming-Hsuan
contents Recent advancements in multimodal large language models (LLMs) have demonstrated significant potential across various domains, particularly in concept reasoning. However, their applications in understanding 3D environments remain limited, primarily offering textual or numerical outputs without generating dense, informative segmentation masks. This paper introduces Reason3D, a novel LLM designed for comprehensive 3D understanding. Reason3D processes point cloud data and text prompts to produce textual responses and segmentation masks, enabling advanced tasks such as 3D reasoning segmentation, hierarchical searching, express referring, and question answering with detailed mask outputs. We propose a hierarchical mask decoder that employs a coarse-to-fine approach to segment objects within expansive scenes. It begins with a coarse location estimation, followed by object mask estimation, using two unique tokens predicted by LLMs based on the textual query. Experimental results on large-scale ScanNet and Matterport3D datasets validate the effectiveness of our Reason3D across various tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17427
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model
Huang, Kuan-Chih
Li, Xiangtai
Qi, Lu
Yan, Shuicheng
Yang, Ming-Hsuan
Computer Vision and Pattern Recognition
Recent advancements in multimodal large language models (LLMs) have demonstrated significant potential across various domains, particularly in concept reasoning. However, their applications in understanding 3D environments remain limited, primarily offering textual or numerical outputs without generating dense, informative segmentation masks. This paper introduces Reason3D, a novel LLM designed for comprehensive 3D understanding. Reason3D processes point cloud data and text prompts to produce textual responses and segmentation masks, enabling advanced tasks such as 3D reasoning segmentation, hierarchical searching, express referring, and question answering with detailed mask outputs. We propose a hierarchical mask decoder that employs a coarse-to-fine approach to segment objects within expansive scenes. It begins with a coarse location estimation, followed by object mask estimation, using two unique tokens predicted by LLMs based on the textual query. Experimental results on large-scale ScanNet and Matterport3D datasets validate the effectiveness of our Reason3D across various tasks.
title Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.17427