Optimizing Through Learned Errors for Accurate Sports Field Registration
2020 IEEE Winter Conference on Applications of Computer Vision (WACV)(2020)
摘要
We propose an optimization-based framework to register sports field templates onto broadcast videos. For accurate registration we go beyond the prevalent feed-forward paradigm. Instead, we propose to train a deep network that regresses the registration error, and then register images by finding the registration parameters that minimize the regressed error. We demonstrate the effectiveness of our method by applying it to real-world sports broadcast videos, outperforming the state of the art. We further apply our method on a synthetic toy example and demonstrate that our method brings significant gains even when the problem is simplified and unlimited training data is available
1
.
更多查看译文
关键词
learned errors,accurate sports field registration,optimization-based framework,deep network,registration error,registration parameters,regressed error,real-world sports broadcast videos,feed-forward paradigm
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要