Multi-view Self-supervised Object Segmentation
文献类型：会议论文
| 作者 | Ma Wenxuan1,2 ; ZhengLiming1,2; Cai Yinghao1; Lu Tao1; Wang Shuo1
|
| 出版日期 | 2023-10 |
| 会议日期 | 2023-10 |
| 会议地点 | Samui, Thailand |
| 关键词 | 具身视觉感知 自监督学习 机器人视觉 |
| 英文摘要 | Robots often operate in open-world environments, where the capability to generalize to new scenarios is crucial for robotic applications such as navigation and manipulation. In this paper, we propose a novel multi-view self-supervised framework (MVSS) to adapt off-the-shelf segmentation methods in a self-supervised manner by leveraging multi-view consistency. Pixel-level and object-level correspondences are established through unsupervised camera pose estimation and cross-frame object association to learn feature embeddings that the same object are close to each other and embeddings from different objects are separated. Experimental results show that it only needs to observe the RGB-D sequence once without any annotation, our proposed method is able to adapt existing methods in new scenarios to achieve performance close to that of supervised segmentation methods. |
| 语种 | 英语 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/57251]  |
| 专题 | 智能机器人系统研究 |
| 通讯作者 | Cai Yinghao |
| 作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 |
| 推荐引用方式 GB/T 7714 | Ma Wenxuan,ZhengLiming,Cai Yinghao,et al. Multi-view Self-supervised Object Segmentation[C]. 见:. Samui, Thailand. 2023-10. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。