Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation | |
Zhou ZM(周正铭)2,3; Dong QL(董秋雷)1,2,3 | |
2022-10 | |
会议日期 | 2022-10-23 |
会议地点 | Tel Aviv, Israel |
英文摘要 | Self-supervised monocular depth estimation has received much attention recently in computer vision. Most of the existing works in literature aggregate multi-scale features for depth prediction via either straightforward concatenation or element-wise addition, however, such feature aggregation operations generally neglect the contextual consistency between multi-scale features. Addressing this problem, we propose the Self-Distilled Feature Aggregation (SDFA) module for simultaneously aggregating a pair of low-scale and high-scale features and maintaining their contextual consistency. The SDFA employs three branches to learn three feature offset maps respectively: one offset map for refining the input low-scale feature and the other two for refining the input high-scale feature under a designed self-distillation manner. Then, we propose an SDFA-based network for self-supervised monocular depth estimation, and design a self-distilled training strategy to train the proposed network with the SDFA module. Experimental results on the KITTI dataset demonstrate that the proposed method outperforms the comparative state-of-the-art methods in most cases. The code is available at https://github.com/ZM-Zhou/SDFA-Net_pytorch. |
会议录出版者 | Springer Science and Business Media Deutschland GmbH |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/51854] |
专题 | 自动化研究所_模式识别国家重点实验室_机器人视觉团队 |
通讯作者 | Dong QL(董秋雷) |
作者单位 | 1.中国科学院脑科学与智能技术卓越创新中心 2.中国科学院大学 3.中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhou ZM,Dong QL. Self-distilled Feature Aggregation for Self-supervised Monocular Depth Estimation[C]. 见:. Tel Aviv, Israel. 2022-10-23. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论