# StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction

arXiv: https://arxiv.org/abs/1807.08865 · HTML: https://mlsanity.com/paper/1807.08865/

## Key facts

- Cited by 88 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2018.

## Built on by (most cited first, 30 of 88)

- [Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation](https://mlsanity.com/paper/2203.11483/) (2022)
- [CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow](https://mlsanity.com/paper/2211.10408/) (2022)
- [SMD-Nets: Stereo Mixture Density Networks](https://mlsanity.com/paper/2104.03866/) (2021)
- [Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitation](https://mlsanity.com/paper/2108.05773/) (2021)
- [Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective](https://mlsanity.com/paper/2203.10887/) (2022)
- [Extreme Rotation Estimation using Dense Correlation Volumes](https://mlsanity.com/paper/2104.13530/) (2021)
- [Neural Markov Random Field for Stereo Matching](https://mlsanity.com/paper/2403.11193/) (2024)
- [StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision](https://mlsanity.com/paper/2104.05289/) (2021)
- [Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching](https://mlsanity.com/paper/2307.14071/) (2023)
- [Tracking and Mapping in Medical Computer Vision: A Review](https://mlsanity.com/paper/2310.11475/) (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)
- [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)
- [Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching](https://mlsanity.com/paper/2512.11130/) (2025)
- [A Decomposition Model for Stereo Matching](https://mlsanity.com/paper/2104.07516/) (2021)
- [A Survey on Deep Stereo Matching in the Twenties](https://mlsanity.com/paper/2407.07816/) (2024)
- [PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas](https://mlsanity.com/paper/2306.01531/) (2023)
- [Feedback Network for Mutually Boosted Stereo Image Super-Resolution and Disparity Estimation](https://mlsanity.com/paper/2106.00985/) (2021)
- [Binary TTC: A Temporal Geofence for Autonomous Navigation](https://mlsanity.com/paper/2101.04777/) (2021)
- [Global Occlusion-Aware Transformer for Robust Stereo Matching](https://mlsanity.com/paper/2312.14650/) (2023)
- [iSLAM: Imperative SLAM](https://mlsanity.com/paper/2306.07894/) (2023)
- [A Learned Stereo Depth System for Robotic Manipulation in Homes](https://mlsanity.com/paper/2109.11644/) (2021)
- [Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality](https://mlsanity.com/paper/2309.04183/) (2023)
- [Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos](https://mlsanity.com/paper/2403.17915/) (2024)
- [TemporalStereo: Efficient Spatial-Temporal Stereo Matching Network](https://mlsanity.com/paper/2211.13755/) (2022)
- [FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation](https://mlsanity.com/paper/2403.03221/) (2024)
- [FADNet++: Real-Time and Accurate Disparity Estimation with Configurable Networks](https://mlsanity.com/paper/2110.02582/) (2021)
- [Facial Depth and Normal Estimation using Single Dual-Pixel Camera](https://mlsanity.com/paper/2111.12928/) (2021)
- [Struct-MDC: Mesh-Refined Unsupervised Depth Completion Leveraging Structural Regularities from Visual SLAM](https://mlsanity.com/paper/2204.13877/) (2022)

## Abstract (arXiv)

This paper presents StereoNet, the first end-to-end deep architecture for real-time stereo matching that runs at 60 fps on an NVidia Titan X, producing high-quality, edge-preserved, quantization-free disparity maps. A key insight of this paper is that the network achieves a sub-pixel matching precision than is a magnitude higher than those of traditional stereo matching approaches. This allows us to achieve real-time performance by using a very low resolution cost volume that encodes all the information needed to achieve high disparity precision. Spatial precision is achieved by employing a learned edge-aware upsampling function. Our model uses a Siamese network to extract features from the left and right image. A first estimate of the disparity is computed in a very low resolution cost volume, then hierarchically the model re-introduces high-frequency details through a learned upsampling function that uses compact pixel-to-pixel refinement networks. Leveraging color input as a guide, this function is capable of producing high-quality edge-aware output. We achieve compelling results on multiple benchmarks, showing how the proposed method offers extreme flexibility at an acceptable computational budget.