FlowNet3D++: Geometric losses for deep scene flow estimation

We present FlowNet3D++, a deep scene flow estimation network. Inspired by classical methods, FlowNet3D++ incorporates geometric constraints in the form of point-toplane distance and angular alignment between individual vectors in the flow field, into FlowNet3D [21]. We demonstrate that the addition...

Celý popis

Podrobná bibliografie
Hlavní autoři: Wang, Z, Li, S, Howard-Jenkins, H, Prisacariu, VA, Chen, M
Médium: Conference item
Jazyk:English
Vydáno: IEEE 2020