SegPoint: Segment Any Point Cloud via Large Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: He, Shuting, Ding, Henghui, Jiang, Xudong, Wen, Bihan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916329759440896
author He, Shuting
Ding, Henghui
Jiang, Xudong
Wen, Bihan
author_facet He, Shuting
Ding, Henghui
Jiang, Xudong
Wen, Bihan
contents Despite significant progress in 3D point cloud segmentation, existing methods primarily address specific tasks and depend on explicit instructions to identify targets, lacking the capability to infer and understand implicit user intentions in a unified framework. In this work, we propose a model, called SegPoint, that leverages the reasoning capabilities of a multi-modal Large Language Model (LLM) to produce point-wise segmentation masks across a diverse range of tasks: 1) 3D instruction segmentation, 2) 3D referring segmentation, 3) 3D semantic segmentation, and 4) 3D open-vocabulary semantic segmentation. To advance 3D instruction research, we introduce a new benchmark, Instruct3D, designed to evaluate segmentation performance from complex and implicit instructional texts, featuring 2,565 point cloud-instruction pairs. Our experimental results demonstrate that SegPoint achieves competitive performance on established benchmarks such as ScanRefer for referring segmentation and ScanNet for semantic segmentation, while delivering outstanding outcomes on the Instruct3D dataset. To our knowledge, SegPoint is the first model to address these varied segmentation tasks within a single framework, achieving satisfactory performance.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13761
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SegPoint: Segment Any Point Cloud via Large Language Model
He, Shuting
Ding, Henghui
Jiang, Xudong
Wen, Bihan
Computer Vision and Pattern Recognition
Despite significant progress in 3D point cloud segmentation, existing methods primarily address specific tasks and depend on explicit instructions to identify targets, lacking the capability to infer and understand implicit user intentions in a unified framework. In this work, we propose a model, called SegPoint, that leverages the reasoning capabilities of a multi-modal Large Language Model (LLM) to produce point-wise segmentation masks across a diverse range of tasks: 1) 3D instruction segmentation, 2) 3D referring segmentation, 3) 3D semantic segmentation, and 4) 3D open-vocabulary semantic segmentation. To advance 3D instruction research, we introduce a new benchmark, Instruct3D, designed to evaluate segmentation performance from complex and implicit instructional texts, featuring 2,565 point cloud-instruction pairs. Our experimental results demonstrate that SegPoint achieves competitive performance on established benchmarks such as ScanRefer for referring segmentation and ScanNet for semantic segmentation, while delivering outstanding outcomes on the Instruct3D dataset. To our knowledge, SegPoint is the first model to address these varied segmentation tasks within a single framework, achieving satisfactory performance.
title SegPoint: Segment Any Point Cloud via Large Language Model
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.13761