Main Content

Stereo Vision

Stereo rectification, disparity, and dense 3-D reconstruction

Stereo vision is the process of recovering depth from camera images by comparing two or more views of the same scene. The output of this computation is a 3-D point cloud, where each 3-D point corresponds to a pixel in one of the images.

Stereo image rectification projects images onto a common image plane in such a way that the corresponding points have the same row coordinates. This process is useful for stereo vision, because the 2-D stereo correspondence problem reduces to a 1-D problem. As an example, stereo image rectification is often used as a preprocessing step for computing disparity or creating anaglyph images.

Stereo Camera Calibrator display


Camera CalibratorEstimate geometric parameters of a single camera
Stereo Camera CalibratorEstimate geometric parameters of a stereo camera


expand all

triangulate3-D locations of undistorted matching points in stereo images
epipolarLineCompute epipolar lines for stereo images
isEpipoleInImageDetermine whether image contains epipole
undistortImageCorrect image for lens distortion
undistortPointsCorrect point coordinates for lens distortion
disparityBMCompute disparity map using block matching
disparitySGMCompute disparity map through semi-global matching
estimateStereoRectificationUncalibrated stereo rectification (Since R2022b)
lineToBorderPointsIntersection points of lines in image and image border
reconstructSceneReconstruct 3-D scene from disparity map
rectifyStereoImagesRectify pair of stereo images
stereoParametersObject for storing stereo camera system parameters
stereoAnaglyphCreate red-cyan anaglyph from stereo pair of images
pcshowPlot 3-D point cloud
plotCameraPlot a camera in 3-D coordinates
rotmat2vec3dConvert 3-D rotation matrix to rotation vector (Since R2022b)
rotvec2mat3dConvert 3-D rotation vector to rotation matrix (Since R2022b)