Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics
CoRR(2019)
摘要
We present an approach which takes advantage of both structure and semantics for unsupervised monocular learning of depth and ego-motion. More specifically we model the motions of individual objects and learn their 3D motion vector jointly with depth and ego-motion. We obtain more accurate results, especially for challenging dynamic scenes not addressed by previous approaches. This is an extended version of Casser et al. [1]. Code and models have been open sourced at: https://sites.google.com/corp/view/struct2depth.
更多查看译文
关键词
unsupervised monocular ego-motion learning,3D motion vector,unsupervised monocular depth learning
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