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...
Main Authors: | Wang, Z, Li, S, Howard-Jenkins, H, Prisacariu, VA, Chen, M |
---|---|
格式: | Conference item |
语言: | English |
出版: |
IEEE
2020
|
相似书籍
-
SA‐FlowNet: Event‐based self‐attention optical flow estimation with spiking‐analogue neural networks
由: Fan Yang, et al.
出版: (2023-12-01) -
AM3F-FlowNet: Attention-Based Multi-Scale Multi-Branch Flow Network
由: Chenghao Fu, et al.
出版: (2023-07-01) -
JOINT 3D ESTIMATION OF VEHICLES AND SCENE FLOW
由: M. Menze, et al.
出版: (2015-08-01) -
Deep flow-net for EPI distortion estimation
由: Benjamin Zahneisen, et al.
出版: (2020-08-01) -
Diameter Estimate in Geometric Flows
由: Shouwen Fang, et al.
出版: (2023-11-01)