English

SegVec3D: A Method for Vector Embedding of 3D Objects Oriented Towards Robot manipulation

Computer Vision and Pattern Recognition 2025-07-15 v1 Robotics

Abstract

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.

Keywords

Cite

@article{arxiv.2507.09459,
  title  = {SegVec3D: A Method for Vector Embedding of 3D Objects Oriented Towards Robot manipulation},
  author = {Zhihan Kang and Boyu Wang},
  journal= {arXiv preprint arXiv:2507.09459},
  year   = {2025}
}

Comments

Undergraduate Theis; 12 pages, 6 figures

R2 v1 2026-07-01T03:58:16.803Z