# AutoDispNet: Improving Disparity Estimation With AutoML

arXiv: https://arxiv.org/abs/1905.07443 · HTML: https://mlsanity.com/paper/1905.07443/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 May 2019.

## Built on by (most cited first, 29 of 29)

- [Neural Architecture Search: Insights from 1000 Papers](https://mlsanity.com/paper/2301.08727/) (2023)
- [MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching](https://mlsanity.com/paper/2108.09770/) (2021)
- [Learning Depth Estimation for Transparent and Mirror Surfaces](https://mlsanity.com/paper/2307.15052/) (2023)
- [OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline](https://mlsanity.com/paper/2312.00343/) (2023)
- [Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization](https://mlsanity.com/paper/2105.01015/) (2021)
- [Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalization](https://mlsanity.com/paper/2312.09254/) (2023)
- [Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception](https://mlsanity.com/paper/2110.04988/) (2021)
- [Neural Architecture Search for Dense Prediction Tasks in Computer Vision](https://mlsanity.com/paper/2202.07242/) (2022)
- [FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks](https://mlsanity.com/paper/2110.02582/) (2021)
- [Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline](https://mlsanity.com/paper/2205.02692/) (2022)
- [An Improved RaftStereo Trained with A Mixed Dataset for the Robust Vision Challenge 2022](https://mlsanity.com/paper/2210.12785/) (2022)
- [Active Stereo Without Pattern Projector](https://mlsanity.com/paper/2309.12315/) (2023)
- [Lightweight Monocular Depth with a Novel Neural Architecture Search Method](https://mlsanity.com/paper/2108.11105/) (2021)
- [AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach](https://mlsanity.com/paper/2112.04974/) (2021)
- [LiDAR-Event Stereo Fusion with Hallucinations](https://mlsanity.com/paper/2408.04633/) (2024)
- [Bag of Tricks for Neural Architecture Search](https://mlsanity.com/paper/2107.03719/) (2021)
- [The Potential of AutoML for Recommender Systems](https://mlsanity.com/paper/2402.04453/) (2024)
- [NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces](https://mlsanity.com/paper/2506.05815/) (2025)
- [An Approach for Combining Multimodal Fusion and Neural Architecture Search Applied to Knowledge Tracing](https://mlsanity.com/paper/2111.04497/) (2021)
- [EASNet: Searching Elastic and Accurate Network Architecture for Stereo Matching](https://mlsanity.com/paper/2207.09796/) (2022)
- [Reusable Architecture Growth for Continual Stereo Matching](https://mlsanity.com/paper/2404.00360/) (2024)
- [AdaSpring: Context-adaptive and Runtime-evolutionary Deep Model Compression for Mobile Applications](https://mlsanity.com/paper/2101.11800/) (2021)
- [Meta-Learning of NAS for Few-shot Learning in Medical Image Applications](https://mlsanity.com/paper/2203.08951/) (2022)
- [TopoNAS: Boosting Search Efficiency of Gradient-based NAS via Topological Simplification](https://mlsanity.com/paper/2408.01311/) (2024)
- [Fast Neural Architecture Search for Lightweight Dense Prediction Networks](https://mlsanity.com/paper/2203.01994/) (2022)
- [FlowNAS: Neural Architecture Search for Optical Flow Estimation](https://mlsanity.com/paper/2207.01271/) (2022)
- [Active Stereo in the Wild through Virtual Pattern Projection](https://mlsanity.com/paper/2406.04345/) (2024)
- [LeanStereo: A Leaner Backbone based Stereo Network](https://mlsanity.com/paper/2503.18557/) (2025)
- [ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching](https://mlsanity.com/paper/2506.21091/) (2025)

## Abstract (arXiv)

Much research work in computer vision is being spent on optimizing existing network architectures to obtain a few more percentage points on benchmarks. Recent AutoML approaches promise to relieve us from this effort. However, they are mainly designed for comparatively small-scale classification tasks. In this work, we show how to use and extend existing AutoML techniques to efficiently optimize large-scale U-Net-like encoder-decoder architectures. In particular, we leverage gradient-based neural architecture search and Bayesian optimization for hyperparameter search. The resulting optimization does not require a large-scale compute cluster. We show results on disparity estimation that clearly outperform the manually optimized baseline and reach state-of-the-art performance.