Camera Intrinsics

Estimate a camera's intrinsic parameters (focal length and principal point, with optional lens distortion) from one to five images of the same scene. Use it as a prior when you don't have factory calibration data for a camera.

All images in a single request must come from the same camera at the same resolution. Sending 1–5 images of the same scene improves the estimate. Images of different resolutions (or from different cameras) are rejected.

Camera Intrinsics API

Make a POST request to /v1/vps/camera-intrinsics with your authentication token. The request is multipart/form-data:

• images: 1 to 5 image files (field name images). Each file must be an image and ≤ 15 MB.

• cameraModel: optional string, one of pinhole (default), simple_radial, radial, simple_divisional. Use a distortion model (simple_radial / radial / simple_divisional) for wide-angle or fisheye lenses.

The endpoint is synchronous and returns the estimated intrinsics in the response.

Sample Request

curl -X POST "https://api.multiset.ai/v1/vps/camera-intrinsics" \
  -H "Authorization: Bearer <ACCESS_TOKEN>" \
  -F "images=@frame_01.jpg" \
  -F "images=@frame_02.jpg" \
  -F "cameraModel=pinhole"

Sample Response

{
    "requestId": "b1c2d3e4-....",
    "cameraModel": "pinhole",
    "imageCount": 2,
    "intrinsics": { "fx": 1462.3, "fy": 1462.3, "px": 960.0, "py": 540.0 },
    "resolution": { "width": 1920, "height": 1080 },
    "focalUncertainty": 12.4,
    "focalUncertaintyRatio": 0.0085,
    "distortion": null
}

Reading the Result

• intrinsics.fx / intrinsics.fy: focal length in pixels. px / py: the principal point (image centre).

• resolution: the pixel dimensions the intrinsics correspond to. If you resize the image, scale the intrinsics by the same factor.

• focalUncertainty / focalUncertaintyRatio: the estimate's uncertainty in pixels and as a fraction of fx. Lower is more confident.

• distortion: present only when a distortion model is requested and coefficients are returned; null for pinhole.

This is a prior/estimate, not a substitute for a full calibration target. Treat the result as a good starting point that a downstream process can refine.

Estimate Camera Intrinsics

post

Estimates camera intrinsics from 1–5 images. All images in a request must come from the same camera at the same resolution. The request is multipart/form-data; the response is returned synchronously.

Authorizations

bearerAuth

AuthorizationstringRequired

JWT token obtained from the authentication endpoint.

Body

multipart/form-data

imagesstring · binary[] · min: 1 · max: 5Required

1 to 5 image files (field name images). Each must be an image and ≤ 15 MB.

cameraModelstring · enumOptional

Distortion model to fit. Use a distorted model for wide-angle/fisheye lenses.

Default: pinholePossible values:

Responses

200

Estimated intrinsics.

application/json

requestIdstringOptionalExample: b1c2d3e4-....

cameraModelstringOptionalExample: pinhole

imageCountintegerOptionalExample: 2

focalUncertaintynumberOptional

1-sigma uncertainty of the focal estimate, in pixels.

Example: 12.4

focalUncertaintyRationumberOptional

focalUncertainty / fx. Present when computable.

Example: 0.0085

distortionany · nullableOptional

Distortion coefficients. Present only for non-pinhole models; null otherwise.

400

Bad Request. No images, more than 5, a file over 15 MB, a non-image file, an invalid cameraModel, or images of differing resolution.

401

Unauthorized. Invalid or expired token.

503

Estimation service temporarily unavailable.

post/vps/camera-intrinsics

HTTPcURLJavaScriptPython

POST /v1/vps/camera-intrinsics HTTP/1.1
Host: api.multiset.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 45

{
  "images": [
    "binary"
  ],
  "cameraModel": "pinhole"
}

{
  "requestId": "b1c2d3e4-....",
  "cameraModel": "pinhole",
  "imageCount": 2,
  "intrinsics": {
    "fx": 1462.3,
    "fy": 1462.3,
    "px": 960,
    "py": 540
  },
  "resolution": {
    "width": 1920,
    "height": 1080
  },
  "focalUncertainty": 12.4,
  "focalUncertaintyRatio": 0.0085,
  "distortion": null
}