CUED Publications database

End-to-End Learning of Geometry and Context for Deep Stereo Regression

Kendall, A and Martirosyan, H and Dasgupta, S and Henry, P and Kennedy, R and Bachrach, A and Bry, A (2017) End-to-End Learning of Geometry and Context for Deep Stereo Regression. In: 2017 IEEE International Conference on Computer Vision (ICCV), 2017-10-22 to 2017-10-29, Venice. (Unpublished)

Full text not available from this repository.


We propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images. We leverage knowledge of the problem's geometry to form a cost volume using deep feature representations. We learn to incorporate contextual information using 3-D convolutions over this volume. Disparity values are regressed from the cost volume using a proposed differentiable soft argmin operation, which allows us to train our method end-to-end to sub-pixel accuracy without any additional post-processing or regularization. We evaluate our method on the Scene Flow and KITTI datasets and on KITTI we set a new state-of-the-art benchmark, while being significantly faster than competing approaches.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Uncontrolled Keywords: cs.CV cs.CV cs.NE
Divisions: Div F > Machine Intelligence
Depositing User: Unnamed user with email
Date Deposited: 02 Feb 2018 20:20
Last Modified: 15 Apr 2021 02:19