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

03/13/2017
by   Alex Kendall, et al.
0

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.

READ FULL TEXT

page 2

page 7

page 9

research
04/19/2019

AMNet: Deep Atrous Multiscale Stereo Disparity Estimation Networks

In this paper, a new deep learning architecture for stereo disparity est...
research
09/09/2019

Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching

State-of-the-art deep learning based stereo matching approaches treat di...
research
08/12/2021

Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation

Volumetric deep learning approach towards stereo matching aggregates a c...
research
12/06/2016

Deep Stereo Matching with Dense CRF Priors

Stereo reconstruction from rectified images has recently been revisited ...
research
05/25/2021

SBEVNet: End-to-End Deep Stereo Layout Estimation

Accurate layout estimation is crucial for planning and navigation in rob...
research
10/26/2020

EDNet: Improved DispNet for Efficient Disparity Estimation

Given a pair of rectified images, the goal of stereo matching is to esti...
research
09/12/2019

DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch

Our goal is to significantly speed up the runtime of current state-of-th...

Please sign up or login with your details

Forgot password? Click here to reset