Skip to content
opencv-wasm

Fundamental and essential matrices

Algorithm atlas3D vision

Constrain where a point from one camera view can appear in another.

Try it on your image ↓

VISUAL WALKTHROUGH3D vision
REFERENCE INPUTScene and camera observations

Two cameras observe the same scene point from different positions.

RESULTConstrain the partner observation

For a calibrated essential matrix, choose a pose consistent with points in front of both cameras.

STEP 03 / 03

For a calibrated essential matrix, choose a pose consistent with points in front of both cameras.

Illustrative example. The stages explain the method; they are not a live OpenCV execution.

Try it on an image

YOUR IMAGE · REAL OPENCV

Experiment at pixel level

Open full lab ↗

Estimate a fundamental matrix from your matching points and draw epipolar lines on the second image. Defaults are illustrative correspondences, not detected features.

The engine loads on your first run. Your images stay in this browser.

Input448 × 320
OutputWaiting for a result

Scroll over either image to zoom at the pointer. Use the scrollbars to pan both views over the same relative area. Zoom is relative to the input; pixel coordinates belong to each image. Warps can change scene correspondence.

Pixel inspector RGBA · native values · matched scale · 9 × 9 output pixels
Hover to inspect. Click to pin a pixel.
Input 
Select a pixel

Output 
Select a pixel

Sample models and licenses

When to use it

Reject inconsistent matches, recover relative camera motion, or prepare a two-view reconstruction.

How it works

  1. 01Match corresponding image points.
  2. 02Estimate the epipolar relation with a robust method.
  3. 03For a calibrated essential matrix, choose a pose consistent with points in front of both cameras.

x₂ᵀ F x₁ = 0

What to tune

Essential geometry needs calibrated or normalized coordinates. Inspect inliers and cheirality, not only the returned matrix.

Where it breaks down

Pure rotation, weak baseline and degenerate scenes can prevent reliable depth or translation estimates. Translation recovered from an essential matrix has unknown scale.

TypeScript API

Open an entry for its exact overloads, parameter descriptions, result ownership and pinned upstream source.

findFundamentalMatReference →findEssentialMatReference →recoverPoseReference →computeCorrespondEpilinesReference →

All of these calls execute on the CPU. Native objects need explicit disposal. See matrices and ownership and build compatibility.

Camera calibration

Estimate a camera’s intrinsic parameters and lens distortion from known target geometry.

Lens undistortion

Invert a calibrated lens model to map distorted observations onto an idealized camera image.

Perspective-n-point pose

Estimate a camera-relative object pose from known 3D points and their 2D image observations.

Stereo block matching

Find horizontal correspondences between rectified stereo images using local block similarity.