AMNet: Deep Atrous Multiscale Stereo Disparity Estimation Networks

04/19/2019
by   Xianzhi Du, et al.
10

In this paper, a new deep learning architecture for stereo disparity estimation is proposed. The proposed atrous multiscale network (AMNet) adopts an efficient feature extractor with depthwise-separable convolutions and an extended cost volume that deploys novel stereo matching costs on the deep features. A stacked atrous multiscale network is proposed to aggregate rich multiscale contextual information from the cost volume which allows for estimating the disparity with high accuracy at multiple scales. AMNet can be further modified to be a foreground-background aware network, FBA-AMNet, which is capable of discriminating between the foreground and the background objects in the scene at multiple scales. An iterative multitask learning method is proposed to train FBA-AMNet end-to-end. The proposed disparity estimation networks, AMNet and FBA-AMNet, show accurate disparity estimates and advance the state of the art on the challenging Middlebury, KITTI 2012, KITTI 2015, and Sceneflow stereo disparity estimation benchmarks.

READ FULL TEXT

page 2

page 4

page 8

page 11

page 12

page 13

page 17

page 23

research
03/13/2017

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

We propose a novel deep learning architecture for regressing disparity f...
research
05/25/2021

SBEVNet: End-to-End Deep Stereo Layout Estimation

Accurate layout estimation is crucial for planning and navigation in rob...
research
05/31/2019

DISCO: Depth Inference from Stereo using Context

Recent deep learning based approaches have outperformed classical stereo...
research
05/18/2020

Niose-Sampling Cross Entropy Loss: Improving Disparity Regression Via Cost Volume Aware Regularizer

Recent end-to-end deep neural networks for disparity regression have ach...
research
12/10/2020

Full Matching on Low Resolution for Disparity Estimation

A Multistage Full Matching disparity estimation scheme (MFM) is proposed...
research
07/31/2018

SegStereo: Exploiting Semantic Information for Disparity Estimation

Disparity estimation for binocular stereo images finds a wide range of a...
research
09/13/2018

DispSegNet: Leveraging Semantics for End-to-End Learning of Disparity Estimation from Stereo Imagery

Recent work has shown that convolutional neural networks (CNNs) can be a...

Please sign up or login with your details

Forgot password? Click here to reset