# Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching

arXiv: https://arxiv.org/abs/1806.01677 · HTML: https://mlsanity.com/paper/1806.01677/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2018.

## Built on by (most cited first, 20 of 20)

- [SMD-Nets: Stereo Mixture Density Networks](https://mlsanity.com/paper/2104.03866/) (2021)
- [Multi-Frame Self-Supervised Depth with Transformers](https://mlsanity.com/paper/2204.07616/) (2022)
- [Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation](https://mlsanity.com/paper/2108.05773/) (2021)
- [GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Feature](https://mlsanity.com/paper/2204.00179/) (2022)
- [Neural Markov Random Field for Stereo Matching](https://mlsanity.com/paper/2403.11193/) (2024)
- [Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks](https://mlsanity.com/paper/2112.01011/) (2021)
- [Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching](https://mlsanity.com/paper/2306.15612/) (2023)
- [Data-Driven Feature Tracking for Event Cameras With and Without Frames](https://mlsanity.com/paper/2211.12826/) (2022)
- [TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network](https://mlsanity.com/paper/2211.13755/) (2022)
- [Digging into Depth Priors for Outdoor Neural Radiance Fields](https://mlsanity.com/paper/2308.04413/) (2023)
- [ResDepth: A Deep Residual Prior For 3D Reconstruction From High-resolution Satellite Images](https://mlsanity.com/paper/2106.08107/) (2021)
- [Video Frame Interpolation with Stereo Event and Intensity Camera](https://mlsanity.com/paper/2307.08228/) (2023)
- [Separable Convolutions for Optimizing 3D Stereo Networks](https://mlsanity.com/paper/2108.10216/) (2021)
- [Outdoor Monocular Depth Estimation: A Research Review](https://mlsanity.com/paper/2205.01399/) (2022)
- [Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images](https://mlsanity.com/paper/2104.06782/) (2021)
- [The Sampling-Gaussian for stereo matching](https://mlsanity.com/paper/2410.06527/) (2024)
- [A novel stereo matching pipeline with robustness and unfixed disparity search range](https://mlsanity.com/paper/2204.04865/) (2022)
- [MIDAS: Modeling Ground-Truth Distributions with Dark Knowledge for Domain Generalized Stereo Matching](https://mlsanity.com/paper/2503.04376/) (2025)
- [CMD: Constraining Multimodal Distribution for Domain Adaptation in Stereo Matching](https://mlsanity.com/paper/2504.21302/) (2025)
- [EMCStereo: Attention-Enhanced Stereo Matching for Thin-Structure Depth Estimation with a Synthetic Tree-Branch Benchmark](https://mlsanity.com/paper/2609.13233/) (2026)

## Abstract (arXiv)

End-to-end deep-learning networks recently demonstrated extremely good perfor- mance for stereo matching. However, existing networks are difficult to use for practical applications since (1) they are memory-hungry and unable to process even modest-size images, (2) they have to be trained for a given disparity range. The Practical Deep Stereo (PDS) network that we propose addresses both issues: First, its architecture relies on novel bottleneck modules that drastically reduce the memory footprint in inference, and additional design choices allow to handle greater image size during training. This results in a model that leverages large image context to resolve matching ambiguities. Second, a novel sub-pixel cross- entropy loss combined with a MAP estimator make this network less sensitive to ambiguous matches, and applicable to any disparity range without re-training. We compare PDS to state-of-the-art methods published over the recent months, and demonstrate its superior performance on FlyingThings3D and KITTI sets.