Saved in:
Bibliographic Details
Main Authors: Kang, Zhihan, Wang, Boyu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.09459
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913939135135744
author Kang, Zhihan
Wang, Boyu
author_facet Kang, Zhihan
Wang, Boyu
contents We propose SegVec3D, a novel framework for 3D point cloud instance segmentation that integrates attention mechanisms, embedding learning, and cross-modal alignment. The approach builds a hierarchical feature extractor to enhance geometric structure modeling and enables unsupervised instance segmentation via contrastive clustering. It further aligns 3D data with natural language queries in a shared semantic space, supporting zero-shot retrieval. Compared to recent methods like Mask3D and ULIP, our method uniquely unifies instance segmentation and multimodal understanding with minimal supervision and practical deployability.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09459
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SegVec3D: A Method for Vector Embedding of 3D Objects Oriented Towards Robot manipulation
Kang, Zhihan
Wang, Boyu
Computer Vision and Pattern Recognition
Robotics
We propose SegVec3D, a novel framework for 3D point cloud instance segmentation that integrates attention mechanisms, embedding learning, and cross-modal alignment. The approach builds a hierarchical feature extractor to enhance geometric structure modeling and enables unsupervised instance segmentation via contrastive clustering. It further aligns 3D data with natural language queries in a shared semantic space, supporting zero-shot retrieval. Compared to recent methods like Mask3D and ULIP, our method uniquely unifies instance segmentation and multimodal understanding with minimal supervision and practical deployability.
title SegVec3D: A Method for Vector Embedding of 3D Objects Oriented Towards Robot manipulation
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2507.09459