Embedded real-time stereo estimation via Semi-Global Matching on the GPU
Not on the map. Why?
Abstract (arXiv)
Dense, robust and real-time computation of depth information from stereo-camera systems is a computationally demanding requirement for robotics, advanced driver assistance systems (ADAS) and autonomous vehicles. Semi-Global Matching (SGM) is a widely used algorithm that propagates consistency constraints along several paths across the image. This work presents a real-time system producing reliable disparity estimation results on the new embedded energy-efficient GPU devices. Our design runs on a Tegra X1 at 42 frames per second (fps) for an image size of 640x480, 128 disparity levels, and using 4 path directions for the SGM method.
Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Oct 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 4; 2023: 1; 2024: 2; 2025: 2; 2026: 1.
13 papers.
Sort:
By area:
- 2021Learning High-Speed Flight in the Wildcited by 98
- 2024Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Modelscited by 6
- 2021ReS2tAC -- UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devicescited by 2
- 2023StereoVAE: A lightweight stereo-matching system using embedded GPUscited by 2
- 2024An evaluation of Deep Learning based stereo dense matching dataset shift from aerial images and a large scale stereo datasetcited by 2
- 2022Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?cited by 1
- 2022Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matchingcited by 1
- 2022Efficient stereo matching on embedded GPUs with zero-means cross correlationcited by 1
- 2021FaSS-MVS -- Fast Multi-View Stereo with Surface-Aware Semi-Global Matching from UAV-borne Monocular Imagerycited by 0
- 2022Real-Time High-Quality Stereo Matching System on a GPUcited by 0
- 2025A Reinforcement Learning Method for Environments with Stochastic Variables: Post-Decision Proximal Policy Optimization with Dual Critic Networkscited by 0
- 2025ADEPT: Adaptive Diffusion Environment for Policy Transfer Sim-to-Realcited by 0
- 2026Object-Centric Stereo Ranging for Autonomous Driving: From Dense Disparity to Census-Based Template Matching9 Apr 2026
- 2025ADEPT: Adaptive Diffusion Environment for Policy Transfer Sim-to-Real2 Jun 2025
- 2025A Reinforcement Learning Method for Environments with Stochastic Variables: Post-Decision Proximal Policy Optimization with Dual Critic Networks7 Apr 2025
- 2024Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models18 May 2024
- 2024An evaluation of Deep Learning based stereo dense matching dataset shift from aerial images and a large scale stereo dataset19 Feb 2024
- 2023StereoVAE: A lightweight stereo-matching system using embedded GPUs19 May 2023
- 2022Real-Time High-Quality Stereo Matching System on a GPU1 Dec 2022
- 2022Efficient stereo matching on embedded GPUs with zero-means cross correlation1 Dec 2022
- 2022Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching4 Oct 2022
- 2022Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?28 Jun 2022
- 2021FaSS-MVS -- Fast Multi-View Stereo with Surface-Aware Semi-Global Matching from UAV-borne Monocular Imagery1 Dec 2021
- 2021Learning High-Speed Flight in the Wild11 Oct 2021
- 2021Learning High-Speed Flight in the Wildcited by 98
- 2024Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Modelscited by 6
- 2021ReS2tAC -- UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devicescited by 2
- 2023StereoVAE: A lightweight stereo-matching system using embedded GPUscited by 2
- 2024An evaluation of Deep Learning based stereo dense matching dataset shift from aerial images and a large scale stereo datasetcited by 2
- 2022Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?cited by 1
- 2022Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matchingcited by 1
- 2022Efficient stereo matching on embedded GPUs with zero-means cross correlationcited by 1
- 2021FaSS-MVS -- Fast Multi-View Stereo with Surface-Aware Semi-Global Matching from UAV-borne Monocular Imagerycited by 0
- 2022Real-Time High-Quality Stereo Matching System on a GPUcited by 0
- 2025A Reinforcement Learning Method for Environments with Stochastic Variables: Post-Decision Proximal Policy Optimization with Dual Critic Networkscited by 0
- 2026Object-Centric Stereo Ranging for Autonomous Driving: From Dense Disparity to Census-Based Template Matchingcited by 0
- 2026Object-Centric Stereo Ranging for Autonomous Driving: From Dense Disparity to Census-Based Template Matching9 Apr 2026
- 2025A Reinforcement Learning Method for Environments with Stochastic Variables: Post-Decision Proximal Policy Optimization with Dual Critic Networks7 Apr 2025
- 2024Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models18 May 2024
- 2024An evaluation of Deep Learning based stereo dense matching dataset shift from aerial images and a large scale stereo dataset19 Feb 2024
- 2023StereoVAE: A lightweight stereo-matching system using embedded GPUs19 May 2023
- 2022Real-Time High-Quality Stereo Matching System on a GPU1 Dec 2022
- 2022Efficient stereo matching on embedded GPUs with zero-means cross correlation1 Dec 2022
- 2022Non-learning Stereo-aided Depth Completion under Mis-projection via Selective Stereo Matching4 Oct 2022
- 2022Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?28 Jun 2022
- 2021FaSS-MVS -- Fast Multi-View Stereo with Surface-Aware Semi-Global Matching from UAV-borne Monocular Imagery1 Dec 2021
- 2021Learning High-Speed Flight in the Wild11 Oct 2021
- 2021ReS2tAC -- UAV-Borne Real-Time SGM Stereo Optimized for Embedded ARM and CUDA Devices15 Jun 2021