Learning Independent Object Motion from Unlabelled Stereoscopic Videos: Difference between revisions
No edit summary |
(→Method) |
||
Line 8: | Line 8: | ||
==Method== | ==Method== | ||
;Key Contributions | |||
* Learning with limited supervision | |||
* Factoring the scene into independent moving objects (main idea of the paper) | |||
* Designing a network architecture using place sweep volumes | |||
;Inputs: | |||
* Image pairs \(\{(I_1^l, I_1^r),..., (I_n^l, I_n^r)\}\) from unlabelled stereo videos | |||
* Object bounding boxes \(B = \{B^1,..., B^j\}\) on the left image \(I_t^l\) from off-the-shelf object detectors | |||
;Goal/Outputs: | |||
* Dense depth map \(D\) | |||
* 3D flow fields \(F = \{F^1,..., F^j\}\) | |||
* Instance masks \(M=\{M^1,..., M^j\}\) | |||
==Architecture== | ==Architecture== |
Revision as of 19:26, 3 June 2020
Learning Independent Object Motion from Unlabelled Stereoscopic Videos (CVPR 2019)
Authors: Zhe Cao, Abhishek Kar, Christian Haene, Jitendra Malik
Affiliations: UC Berkeley, Fyusion Inc, Google
Method
- Key Contributions
- Learning with limited supervision
- Factoring the scene into independent moving objects (main idea of the paper)
- Designing a network architecture using place sweep volumes
- Inputs
- Image pairs \(\{(I_1^l, I_1^r),..., (I_n^l, I_n^r)\}\) from unlabelled stereo videos
- Object bounding boxes \(B = \{B^1,..., B^j\}\) on the left image \(I_t^l\) from off-the-shelf object detectors
- Goal/Outputs
- Dense depth map \(D\)
- 3D flow fields \(F = \{F^1,..., F^j\}\)
- Instance masks \(M=\{M^1,..., M^j\}\)