# DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch

arXiv: https://arxiv.org/abs/1909.05845 · HTML: https://mlsanity.com/paper/1909.05845/

## Key facts

- Cited by 114 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2019.

## Built on by (most cited first, 30 of 114)

- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021)
- [Attention Concatenation Volume for Accurate and Efficient Stereo Matching](https://mlsanity.com/paper/2203.02146/) (2022)
- [SMD-Nets: Stereo Mixture Density Networks](https://mlsanity.com/paper/2104.03866/) (2021)
- [Stereo Correspondence and Reconstruction of Endoscopic Data Challenge](https://mlsanity.com/paper/2101.01133/) (2021)
- [MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matching](https://mlsanity.com/paper/2108.09770/) (2021)
- [Robust Reference-based Super-Resolution via C2-Matching](https://mlsanity.com/paper/2106.01863/) (2021)
- [Accurate and Efficient Stereo Matching via Attention Concatenation Volume](https://mlsanity.com/paper/2209.12699/) (2022)
- [IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching](https://mlsanity.com/paper/2409.00638/) (2024)
- [MVSTER: Epipolar Transformer for Efficient Multi-View Stereo](https://mlsanity.com/paper/2204.07346/) (2022)
- [Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation](https://mlsanity.com/paper/2108.05773/) (2021)
- [Bilateral Grid Learning for Stereo Matching Networks](https://mlsanity.com/paper/2101.01601/) (2021)
- [Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry](https://mlsanity.com/paper/2112.08177/) (2021)
- [MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions](https://mlsanity.com/paper/2104.13325/) (2021)
- [DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow](https://mlsanity.com/paper/2204.00330/) (2022)
- [Neural Markov Random Field for Stereo Matching](https://mlsanity.com/paper/2403.11193/) (2024)
- [Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching](https://mlsanity.com/paper/2307.14071/) (2023)
- [Learning Depth Estimation for Transparent and Mirror Surfaces](https://mlsanity.com/paper/2307.15052/) (2023)
- [Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks](https://mlsanity.com/paper/2112.01011/) (2021)
- [Not Just Streaks: Towards Ground Truth for Single Image Deraining](https://mlsanity.com/paper/2206.10779/) (2022)
- [An Adaptive Framework for Learning Unsupervised Depth Completion](https://mlsanity.com/paper/2106.03010/) (2021)
- [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)
- [The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation](https://mlsanity.com/paper/2108.11550/) (2021)
- [Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video](https://mlsanity.com/paper/2404.09833/) (2024)
- [A Decomposition Model for Stereo Matching](https://mlsanity.com/paper/2104.07516/) (2021)
- [ELFNet: Evidential Local-global Fusion for Stereo Matching](https://mlsanity.com/paper/2308.00728/) (2023)
- [Monitored Distillation for Positive Congruent Depth Completion](https://mlsanity.com/paper/2203.16034/) (2022)
- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matching](https://mlsanity.com/paper/2307.16509/) (2023)

## Abstract (arXiv)

Our goal is to significantly speed up the runtime of current state-of-the-art stereo algorithms to enable real-time inference. Towards this goal, we developed a differentiable PatchMatch module that allows us to discard most disparities without requiring full cost volume evaluation. We then exploit this representation to learn which range to prune for each pixel. By progressively reducing the search space and effectively propagating such information, we are able to efficiently compute the cost volume for high likelihood hypotheses and achieve savings in both memory and computation. Finally, an image guided refinement module is exploited to further improve the performance. Since all our components are differentiable, the full network can be trained end-to-end. Our experiments show that our method achieves competitive results on KITTI and SceneFlow datasets while running in real-time at 62ms.