Knowledge Commons of Institute of Automation,CAS
A Novel Underwater Image Synthesis Method Based on a Pixel-level Self-Supervised Training Strategy | |
Zhiheng Wu1,2; Zhengxing Wu1,2; Yue Lu1,2; Jian Wang1,2; Junzhi Yu1,3 | |
2021-07 | |
会议名称 | IEEE International Conference on Real-time Computing and Robotics (RCAR) |
会议日期 | 2021-7 |
会议地点 | Xining, China |
摘要 | With the rapid development of deep neural networks, underwater vision plays an increasingly important role in the underwater robotic operation. However, the scarce underwater datasets greatly limit the performance of deep learning on underwater visual tasks, further hindering the applications of underwater operation. To solve this problem, we propose an underwater image synthesis method, which can directly convert the natural light image into the synthetic underwater image end-to-end. Particularly, a pixel-level self-supervised training strategy is designed to maximize the structural similarity between the synthesized and real images, through training the real underwater images. Finally, extensive experiments are carried out, and the obtained results demonstrate the effectiveness and superiority of our methods by quantitative and qualitative comparisons. The proposed underwater image synthesis method offers a valuable sight for underwater vision and manipulating control. |
收录类别 | EI |
七大方向——子方向分类 | 图像视频处理与分析 |
国重实验室规划方向分类 | 水下仿生机器人 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52267 |
专题 | 复杂系统认知与决策实验室_水下机器人 |
通讯作者 | Zhengxing Wu |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Peking University |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhiheng Wu,Zhengxing Wu,Yue Lu,et al. A Novel Underwater Image Synthesis Method Based on a Pixel-level Self-Supervised Training Strategy[C],2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
rcar21-216.pdf(1862KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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