Omniseg3d: Omniversal 3d segmentation via hierarchical contrastive learning

[PDF] arxiv.org

EgoLifter: Open-world 3D Segmentation for Egocentric Perception

Q Gu, Z Lv, D Frost, S Green, J Straub… - arXiv preprint arXiv …, 2024 - arxiv.org
In this paper we present EgoLifter, a novel system that can automatically segment scenes
captured from egocentric sensors into a complete decomposition of individual 3D objects …
被引用次数：2 相关文章 所有 2 个版本
[PDF] arxiv.org

Beyond Bare Queries: Open-Vocabulary Object Retrieval with 3D Scene Graph

S Linok, T Zemskova, S Ladanova, R Titkov… - arXiv preprint arXiv …, 2024 - arxiv.org
Locating objects referred to in natural language poses a significant challenge for
autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform …
相关文章 所有 2 个版本
[PDF] arxiv.org

Segment Anything in 3D with Radiance Fields

J Cen, J Fang, Z Zhou, C Yang, L Xie, X Zhang… - arXiv preprint arXiv …, 2023 - arxiv.org
Recently, the Segment Anything Model (SAM) emerged as a powerful vision foundation
model which is capable to segment anything in 2D images. This paper aims to generalize …
相关文章 所有 2 个版本