# FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks

arXiv: https://arxiv.org/abs/2110.02582 · HTML: https://mlsanity.com/paper/2110.02582/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 52 references that are in the map.
- First posted on arXiv 6 Oct 2021.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017)
- [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019)
- [Group-wise Correlation Stereo Network](https://mlsanity.com/paper/1903.04025/) (2019)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)
- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches](https://mlsanity.com/paper/1510.05970/) (2015)
- [Hierarchical Deep Stereo Matching on High-resolution Images](https://mlsanity.com/paper/1912.06704/) (2019)
- [DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch](https://mlsanity.com/paper/1909.05845/) (2019)
- [Learning to Compare Image Patches via Convolutional Neural Networks](https://mlsanity.com/paper/1504.03641/) (2015)
- [Searching for Efficient Multi-Scale Architectures for Dense Image Prediction](https://mlsanity.com/paper/1809.04184/) (2018)
- [StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction](https://mlsanity.com/paper/1807.08865/) (2018)
- [SegStereo: Exploiting Semantic Information for Disparity Estimation](https://mlsanity.com/paper/1807.11699/) (2018)
- [Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation](https://mlsanity.com/paper/1808.01838/) (2018)
- [Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matching](https://mlsanity.com/paper/1708.09204/) (2017)
- [Anytime Stereo Image Depth Estimation on Mobile Devices](https://mlsanity.com/paper/1810.11408/) (2018)
- [Single View Stereo Matching](https://mlsanity.com/paper/1803.02612/) (2018)
- [EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection](https://mlsanity.com/paper/1903.01700/) (2019)
- [FADNet: A Fast and Accurate Network for Disparity Estimation](https://mlsanity.com/paper/2003.10758/) (2020)
- [AutoDispNet: Improving Disparity Estimation With AutoML](https://mlsanity.com/paper/1905.07443/) (2019)
- [CBMV: A Coalesced Bidirectional Matching Volume for Disparity Estimation](https://mlsanity.com/paper/1804.01967/) (2018)

## Built on by (most cited first, 11 of 11)

- [OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline](https://mlsanity.com/paper/2312.00343/) (2023)
- [LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregation](https://mlsanity.com/paper/2406.19833/) (2024)
- [Multi-Modal Multi-Task (3MT) Road Segmentation](https://mlsanity.com/paper/2308.11983/) (2023)
- [Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Data](https://mlsanity.com/paper/2411.14053/) (2024)
- [StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception](https://mlsanity.com/paper/2605.09989/) (2026)
- [EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching](https://mlsanity.com/paper/2207.09796/) (2022)
- [Boosting Zero-shot Stereo Matching using Large-scale Mixed Images Sources in the Real World](https://mlsanity.com/paper/2505.08607/) (2025)
- [VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priors](https://mlsanity.com/paper/2406.02552/) (2024)
- [WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimation](https://mlsanity.com/paper/2605.24074/) (2026)
- [ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching](https://mlsanity.com/paper/2506.21091/) (2025)
- [Decoupling Bidirectional Geometric Representations of 4D cost volume with 2D convolution](https://mlsanity.com/paper/2509.02415/) (2025)

## Abstract (arXiv)

Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better prediction accuracy than traditional hand-crafted feature-based methods. However, the existing DNNs hardly serve both efficient computation and rich expression capability, which makes them difficult for deployment in real-time and high-quality applications, especially on mobile devices. To this end, we propose an efficient, accurate, and configurable deep network for disparity estimation named FADNet++. Leveraging several liberal network design and training techniques, FADNet++ can boost its accuracy with a fast model inference speed for real-time applications. Besides, it enables users to easily configure different sizes of models for balancing accuracy and inference efficiency. We conduct extensive experiments to demonstrate the effectiveness of FADNet++ on both synthetic and realistic datasets among six GPU devices varying from server to mobile platforms. Experimental results show that FADNet++ and its variants achieve state-of-the-art prediction accuracy, and run at a significant order of magnitude faster speed than existing 3D models. With the constraint of running at above 15 frames per second (FPS) on a mobile GPU, FADNet++ achieves a new state-of-the-art result for the SceneFlow dataset.