Learning Independent Object Motion from Unlabelled Stereoscopic Videos: Difference between revisions
No edit summary |
|||
| (One intermediate revision by the same user not shown) | |||
| 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 \(M=\{M^1,..., M^j\}\) | |||
* For each region of interest RoI, predict a per-object flow map using a RCNN | |||
** Also predict a object mask for each RoI | |||
* Construct a full 3D scene flow map using the per-object flow maps. | |||
===Self Supervision and Loss Functions=== | |||
* View Synthesis | |||
* Geometric consistency: The depth values of the warped image and the reference image should match | |||
* Left Right consistency \(L^{lr}\) | |||
* RoI Loss \(L^{roi}\) | |||
* Full image based loss \(L^{t}\) | |||
==Architecture== | ==Architecture== | ||