Edited docs only

release/4.3a0
Frank Dellaert 2025-04-27 00:17:48 -04:00
parent 47812cd899
commit 603caf18b4
3 changed files with 15 additions and 9 deletions

View File

@ -26,7 +26,10 @@
"- **Configuration:** Its behavior (linearization method, handling of degenerate triangulations) is controlled by `SmartProjectionParams`.\n",
"\n",
"**Use Case:** Suitable for Bundle Adjustment or SfM problems where calibration parameters are unknown or need refinement along with camera poses.\n",
"**Alternative:** If calibration is known and fixed, use `SmartProjectionPoseFactor` for better efficiency."
"**Alternative:** If calibration is known and fixed, use `SmartProjectionPoseFactor` for better efficiency.\n",
"\n",
"If you are using the factor, please cite:\n",
"> **L. Carlone, Z. Kira, C. Beall, V. Indelman, F. Dellaert**, \"Eliminating conditionally independent sets in factor graphs: a unifying perspective based on smart factors\", Int. Conf. on Robotics and Automation (ICRA), 2014."
]
},
{

View File

@ -26,7 +26,10 @@
"- **Configuration:** Behavior is controlled by `SmartProjectionParams`.\n",
"\n",
"**Use Case:** Ideal for visual SLAM or SfM when camera intrinsics are pre-calibrated and assumed constant.\n",
"**Alternative:** If calibration also needs optimization, use `SmartProjectionFactor`."
"**Alternative:** If calibration also needs optimization, use `SmartProjectionFactor`.\n",
"\n",
"If you are using the factor, please cite:\n",
"> **L. Carlone, Z. Kira, C. Beall, V. Indelman, F. Dellaert**, \"Eliminating conditionally independent sets in factor graphs: a unifying perspective based on smart factors\", Int. Conf. on Robotics and Automation (ICRA), 2014."
]
},
{

View File

@ -1,26 +1,24 @@
# SLAM Factors and Algorithms
# SLAM
The `slam` module provides a collection of factors, constraints, utilities, and initialization algorithms commonly used in Simultaneous Localization and Mapping (SLAM) and Structure from Motion (SfM) applications. It builds upon the core GTSAM inference engine (`gtsam/inference`) and geometric types (`gtsam/geometry`).
## Core Factors
These are fundamental factor types often used as building blocks in SLAM.
- [BetweenFactor](doc/BetweenFactor.ipynb) : Represents relative measurements between two poses or other Lie group variables (e.g., odometry).
- [PoseRotationPrior](doc/PoseRotationPrior.ipynb) : A prior factor acting only on the rotation component of a pose variable.
- [PoseTranslationPrior](doc/PoseTranslationPrior.ipynb) : A prior factor acting only on the translation component of a pose variable.
- [PriorFactor](doc/PriorFactor.ipynb) : A prior factor acting only on the rotation component of a pose variable.
- [BetweenFactor](doc/BetweenFactor.ipynb) : Represents relative measurements between two poses or other Lie group variables (e.g., derived from [odometry](https://en.wikipedia.org/wiki/Odometry)).
## Visual SLAM/SfM Factors
Factors specifically designed for visual data (camera measurements).
- [GenericProjectionFactor](doc/GenericProjectionFactor.ipynb) : Standard monocular projection factor relating a 3D landmark, camera pose, and fixed calibration to a 2D measurement.
- [StereoFactor](doc/StereoFactor.ipynb) : Standard stereo projection factor relating a 3D landmark, camera pose, and fixed stereo calibration to a `StereoPoint2` measurement.
- [PlanarProjectionFactor](doc/PlanarProjectionFactor.ipynb) : Projection factors specialized for robots moving on a 2D plane.
- [GeneralSFMFactor](doc/GeneralSFMFactor.ipynb) : Projection factors used when camera calibration is unknown or optimized alongside poses and landmarks.
- [StereoFactor](doc/StereoFactor.ipynb) : Standard stereo projection factor relating a 3D landmark, camera pose, and fixed stereo calibration to a `StereoPoint2` measurement.
- [EssentialMatrixFactor](doc/EssentialMatrixFactor.ipynb) : Factors constraining poses or calibration based on the Essential matrix derived from calibrated cameras.
- [EssentialMatrixConstraint](doc/EssentialMatrixConstraint.ipynb) : Factor constraining the relative pose between two cameras based on a measured Essential matrix.
- [TriangulationFactor](doc/TriangulationFactor.ipynb) : Factor constraining a 3D point based on a measurement from a single known camera view, useful for triangulation.
- [PlanarProjectionFactor](doc/PlanarProjectionFactor.ipynb) : Projection factors specialized for robots moving on a 2D plane.
## Smart Factors
@ -36,6 +34,8 @@ Factors that implicitly manage landmark variables, marginalizing them out during
Factors representing various geometric relationships or constraints.
- [PoseRotationPrior](doc/PoseRotationPrior.ipynb) : A prior factor acting only on the rotation component of a pose variable.
- [PoseTranslationPrior](doc/PoseTranslationPrior.ipynb) : A prior factor acting only on the translation component of a pose variable.
- [OrientedPlane3Factor](doc/OrientedPlane3Factor.ipynb) : Factors for estimating and constraining 3D planar landmarks (`OrientedPlane3`).
- [RotateFactor](doc/RotateFactor.ipynb) : Factors constraining an unknown rotation based on how it transforms measured rotations or directions.
- [KarcherMeanFactor](doc/KarcherMeanFactor.ipynb) : Factor for constraining the Karcher mean (geometric average) of a set of rotations or other manifold values.