# AMNet: Deep Atrous Multiscale Stereo Disparity Estimation Networks

arXiv: https://arxiv.org/abs/1904.09099 · HTML: https://mlsanity.com/paper/1904.09099/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2019.

## Built on by (most cited first, 7 of 7)

- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks](https://mlsanity.com/paper/2110.02582/) (2021)
- [An Improved RaftStereo Trained with A Mixed Dataset for the Robust Vision Challenge 2022](https://mlsanity.com/paper/2210.12785/) (2022)
- [Extending 6D Object Pose Estimators for Stereo Vision](https://mlsanity.com/paper/2402.05610/) (2024)
- [Towards Adversarially Robust and Domain Generalizable Stereo Matching by Rethinking DNN Feature Backbones](https://mlsanity.com/paper/2108.00335/) (2021)
- [Distill-then-prune: An Efficient Compression Framework for Real-time Stereo Matching Network on Edge Devices](https://mlsanity.com/paper/2405.11809/) (2024)
- [RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization](https://mlsanity.com/paper/2503.06125/) (2025)

## Abstract (arXiv)

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.