AMNet: Deep Atrous Multiscale Stereo Disparity Estimation Networks
arXiv:1904.09099
Abstract
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.
References in corpus (4)
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
- Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching
Cited by in corpus (11)
- Deep Robust Single Image Depth Estimation Neural Network Using Scene Understanding
- RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching
- FADNet: A Fast and Accurate Network for Disparity Estimation
- KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects
- TW-SMNet: Deep Multitask Learning of Tele-Wide Stereo Matching
- Content-Aware Inter-Scale Cost Aggregation for Stereo Matching
- FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks
- MTStereo 2.0: improved accuracy of stereo depth estimation withMax-trees
- Towards Adversarially Robust and Domain Generalizable Stereo Matching by Rethinking DNN Feature Backbones
- Full Matching on Low Resolution for Disparity Estimation
- Dedge-AGMNet:an effective stereo matching network optimized by depth edge auxiliary task