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