SVO: Semidirect Visual Odometry for Monocular and Multicamera Systems

By Christian Forster, Zichao Zhang, Michael Gassner, Manuel Werlberger, Davide Scaramuzza. 2017

887 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “, edges) [73], [84]; semidirect”
A Benchmark Comparison of Monocular Visual-Inertial Odometry Algorithms for Flying Robots (2018, methodology): “The visual odometry system that serves as the frontend for two of the methods considered in this paper, SVO [5], has been evaluated on the EuRoC datasets [12], but only compares to other noninertial methods.”
A Tutorial on Quantitative Trajectory Evaluation for Visual(-Inertial) Odometry (2018, methodology): “ATE is also widely used to evaluate visual odometry/SLAM algorithms, for example, in [2], [3], [4].”
Extending Monocular Visual Odometry to Stereo Camera Systems by Scale optimization (2019, background): “extended their monocular SVO [2] for multicamera systems [14], though not particularly for a stereo camera.”
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM (2020, methodology): “The hybrid system SVO [23], [24] extracts FAST features, uses a direct method to track features, and any pixel with nonzero intensity gradient, from frame to frame, and optimizes camera trajectory and 3D structure using reprojection error.”
Planning and Decision-Making for Autonomous Vehicles (2018, background): “0 (52), and LSD-SLAM (Large-Scale Direct Monocular SLAM) (53), have matured to be able to compete.”
PL-SLAM: A Stereo SLAM System Through the Combination of Points and Line Segments (2017, methodology): “For future work, our implementation can benefit from faster keypoint front-ends, such as the ones in SVO [10], [26] and”
A Comprehensive Survey of Visual SLAM Algorithms (2022, background): “The authors already proposed an extended version of the SVO, SVO 2.0 [42], in which the algorithm is capable of processing stereo data and IMU information.”
BAD SLAM: Bundle Adjusted Direct RGB-D SLAM (2019, background): “[16, 17] combine direct localization of image patches with indirect BA optimizing the reprojection error.”
FAST-LIO2: Fast Direct LiDAR-Inertial Odometry (2021, background): “Vision-based SLAM [1]–[4] is very accurate in localization but maintains only a sparse feature map and suffers from illumination variation and severe motion blur.”
PL-SLAM: Real-time monocular visual SLAM with points and lines (2017, methodology): “Other semi-direct methods such as [9] overcome the highcomputation requirement of dense methods by exploiting only pixels with strong gradients, providing an intermediate level of accuracy, density and complexity.”