# Stereo DSO: Large-Scale Direct Sparse Visual Odometry with Stereo Cameras

arXiv: https://arxiv.org/abs/1708.07878 · HTML: https://mlsanity.com/paper/1708.07878/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Aug 2017.

## Built on by (most cited first, 30 of 45)

- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Deep Patch Visual Odometry](https://mlsanity.com/paper/2208.04726/) (2022)
- [LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry](https://mlsanity.com/paper/2401.01887/) (2024)
- [DSP-SLAM: Object Oriented SLAM with Deep Shape Priors](https://mlsanity.com/paper/2108.09481/) (2021)
- [DDN-SLAM: Real-time Dense Dynamic Neural Implicit SLAM](https://mlsanity.com/paper/2401.01545/) (2024)
- [MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry](https://mlsanity.com/paper/2409.09479/) (2024)
- [Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter](https://mlsanity.com/paper/2208.01489/) (2022)
- [PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility](https://mlsanity.com/paper/2108.08943/) (2021)
- [Improving Monocular Visual Odometry Using Learned Depth](https://mlsanity.com/paper/2204.01268/) (2022)
- [Benchmarking Egocentric Visual-Inertial SLAM at City Scale](https://mlsanity.com/paper/2509.26639/) (2025)
- [LF-VIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras with Negative Plane](https://mlsanity.com/paper/2202.12613/) (2022)
- [LF-VISLAM: A SLAM Framework for Large Field-of-View Cameras with Negative Imaging Plane on Mobile Agents](https://mlsanity.com/paper/2209.05167/) (2022)
- [Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planning](https://mlsanity.com/paper/2306.01980/) (2023)
- [DVI-SLAM: A Dual Visual Inertial SLAM Network](https://mlsanity.com/paper/2309.13814/) (2023)
- [Towards Scale Consistent Monocular Visual Odometry by Learning from the Virtual World](https://mlsanity.com/paper/2203.05712/) (2022)
- [A Review on Visual-SLAM: Advancements from Geometric Modelling to Learning-based Semantic Scene Understanding](https://mlsanity.com/paper/2209.05222/) (2022)
- [AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach](https://mlsanity.com/paper/2112.04974/) (2021)
- [DeepAVO: Efficient Pose Refining with Feature Distilling for Deep Visual Odometry](https://mlsanity.com/paper/2105.09899/) (2021)
- [UP-SLAM: Adaptively Structured Gaussian SLAM with Uncertainty Prediction in Dynamic Environments](https://mlsanity.com/paper/2505.22335/) (2025)
- [4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions](https://mlsanity.com/paper/2301.01147/) (2022)
- [AdaSfM: From Coarse Global to Fine Incremental Adaptive Structure from Motion](https://mlsanity.com/paper/2301.12135/) (2023)
- [Tight Integration of Feature-based Relocalization in Monocular Direct Visual Odometry](https://mlsanity.com/paper/2102.01191/) (2021)
- [Vision-based Large-scale 3D Semantic Mapping for Autonomous Driving Applications](https://mlsanity.com/paper/2203.01087/) (2022)
- [E-Graph: Minimal Solution for Rigid Rotation with Extensibility Graphs](https://mlsanity.com/paper/2207.10008/) (2022)
- [LiFCal: Online Light Field Camera Calibration via Bundle Adjustment](https://mlsanity.com/paper/2408.11682/) (2024)
- [VGF-Net: Visual-Geometric Fusion Learning for Simultaneous Drone Navigation and Height Mapping](https://mlsanity.com/paper/2104.03109/) (2021)
- [R3LIVE++: A Robust, Real-time, Radiance reconstruction package with a tightly-coupled LiDAR-Inertial-Visual state Estimator](https://mlsanity.com/paper/2209.03666/) (2022)
- [RoMeO: Robust Metric Visual Odometry](https://mlsanity.com/paper/2412.11530/) (2024)
- [Revisiting Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2103.12496/) (2021)
- [TEScalib: Targetless Extrinsic Self-Calibration of LiDAR and Stereo Camera for Automated Driving Vehicles with Uncertainty Analysis](https://mlsanity.com/paper/2202.13847/) (2022)

## Abstract (arXiv)

We propose Stereo Direct Sparse Odometry (Stereo DSO) as a novel method for highly accurate real-time visual odometry estimation of large-scale environments from stereo cameras. It jointly optimizes for all the model parameters within the active window, including the intrinsic/extrinsic camera parameters of all keyframes and the depth values of all selected pixels. In particular, we propose a novel approach to integrate constraints from static stereo into the bundle adjustment pipeline of temporal multi-view stereo. Real-time optimization is realized by sampling pixels uniformly from image regions with sufficient intensity gradient. Fixed-baseline stereo resolves scale drift. It also reduces the sensitivities to large optical flow and to rolling shutter effect which are known shortcomings of direct image alignment methods. Quantitative evaluation demonstrates that the proposed Stereo DSO outperforms existing state-of-the-art visual odometry methods both in terms of tracking accuracy and robustness. Moreover, our method delivers a more precise metric 3D reconstruction than previous dense/semi-dense direct approaches while providing a higher reconstruction density than feature-based methods.