Ctrlk
Developer PortalDemosGithub
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Map Query

The three VPS query endpoints that return a 6-DoF pose, JSON body, form data and multi image, plus every optional query parameter.

The Map Query API returns a device's 6-DoF pose inside a map you have already scanned. Three endpoints do this, and they share the same response shape and the same optional parameters.

Endpoint
Body
Images
Use it for

POST /vps/map/query

JSON

1, base64 encoded

The standard single-frame query, around 1 second

POST /vps/map/query-form

multipart form-data

1, as a file part

The same query when uploading a file is easier than encoding one

POST /vps/map/multi-image-query

multipart form-data

4 to 6, as file parts

A more robust pose in repetitive or difficult scenes

The endpoints come first below, then the parameters that apply across all of them.

VPS Query API

Query your map to get the device position with respect to Map local origin. The query API takes query image (encoded as base64 string) and other image metadata.

The maximum query image resolution is 1280 pixels in either width or height.

Query a VPS map with specific parameters

post
Authorizations
AuthorizationstringRequired
Bearer authentication header of the form Bearer <token>.
Body
mapCodestringOptional

Code to identify the VPS map (required if mapSetCode is not provided)

Example: MAP-X2P23E7Q35VD
mapSetCodestringOptional

Code to identify the map set (required if mapCode is not provided)

Example: MAPSET-ABC123
queryModestring · enumOptional

Localization engine for this query. "vps-1" (default) is the fast standard engine (~2s). "vps-2" is a deep-search engine with up to 15% higher recall and improved accuracy, at higher latency (~3-4s). Ideal for offline or challenging scenes. Also supported on the multi-image query endpoint.

Default: vps-1Example: vps-2Possible values:
hintMapCodesstring[]Optional

List of map codes for spatial hints (only valid with mapSetCode)

Example: ["MAP-X2P23E7Q35VD","MAP-Y3Q34F8R46WE"]
hintPositionnumber[]Optional

Position hint [x, y, z] for spatial filtering. Must be in the map's left-handed (LHS / Unity) coordinate system, the same frame as the position field in a successful localization response (isRightHanded=false).

Example: [2.5,0.1,8]
geoLocationnumber[]Optional

Localize without naming a map. [latitude, longitude] in WGS 84 degrees. The nearest map whose geo-fence lies within geoSearchRadius (default 25m) is resolved and queried; if that map belongs to a map set, the whole set is queried. Distance is measured to the fence edge, so a point inside a fence is 0m. Only active maps with geoFenceReady=true are considered, and 404 is returned when nothing is in range. Mutually exclusive with mapId, mapCode, mapSetId and mapSetCode. It also doubles as geoHint when neither geoHint nor hintPosition is supplied, in which case hintRadius defaults to 100m rather than 25m, because a GPS fix is far less precise than a hint you supplied.

Example: [37.794853,-122.394573]
geoSearchRadiusnumberOptional

Overrides the geo-fence search radius in metres for this request only. Applies only when geoLocation is supplied, and is ignored otherwise. Falls back to 25m.

Example: 50
geoHintnumber[]Optional

Geographic hint [latitude, longitude, altitude], converted to a local hintPosition. WGS 84 degrees for latitude and longitude. Altitude is an ELLIPSOIDAL height in metres (height above the WGS 84 ellipsoid), not mean sea level. Enable use2DFiltering to ignore altitude.

Example: [37.7749,-122.4194,10]
hintRadiusnumber · min: 5 · max: 100Optional

Search radius in meters for spatial filtering (default 25m). Only applies when geoHint or hintPosition is provided. Range 5-100.

Example: 25
use2DFilteringbooleanOptional

When true, skip altitude (Y-axis) in geoHint spatial filtering, using only horizontal distance (X and Z axes). Only applies when geoHint is provided.

Default: falseExample: false
hintFloorHeightnumber[] · min: 2 · max: 2Optional

Floor height band [y_min, y_max] in map-local coordinates. Search run within this vertical range. Works for both single Map and MapSet (positions are in global/MapSet coordinate space). Order does not matter, so [-3, -1] and [-1, -3] both select y ∈ [-3, -1].

Example: [1.5,4.5]
convertToGeoCoordinatesbooleanOptional

Convert result to geographic coordinates (adds GeoPose to response)

Example: false
isRightHandedbooleanOptional

Flag to indicate if response pose is in right-handed coordinate system

Example: false
queryImagestring · base64Required

Base64 encoded image data

Example: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAA8AAAALQCAIAAADQFY7jAAAgAElEQVR4AaS9+5NdR5Lfh34BjW4AxJMgOTN8zCw5OzHriV2vvFrZDjtCVki2Xt5VaKVdybLClsL+3xz23+DQr9ZPlmO16xmvh
Responses
200

Query successful

application/json
poseFoundbooleanRequired

Indicates if the pose was successfully found

Example: true
confidencenumberRequired

Confidence score of the pose estimation

Example: 0.46875
mapIdsstring[]Optional

Array of matched map IDs

Example: ["67e12d4bff7ecf561f2f8a0c"]
mapCodesstring[]Optional

Array of matched map codes

Example: ["MAP_RJFKKWQ1787J"]
responseTimenumberOptional

Response time in milliseconds

Example: 2572
post/vps/map/query
POST /v1/vps/map/query HTTP/1.1
Host: api.multiset.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 710

{
  "mapCode": "MAP-X2P23E7Q35VD",
  "mapSetCode": "MAPSET-ABC123",
  "queryMode": "vps-2",
  "hintMapCodes": [
    "MAP-X2P23E7Q35VD",
    "MAP-Y3Q34F8R46WE"
  ],
  "hintPosition": [
    2.5,
    0.1,
    8
  ],
  "geoLocation": [
    37.794853,
    -122.394573
  ],
  "geoSearchRadius": 50,
  "geoHint": [
    37.7749,
    -122.4194,
    10
  ],
  "hintRadius": 25,
  "use2DFiltering": false,
  "hintFloorHeight": [
    1.5,
    4.5
  ],
  "convertToGeoCoordinates": false,
  "cameraIntrinsics": {
    "fx": 664.3856201171875,
    "fy": 664.3856201171875,
    "px": 478.9782409667969,
    "py": 364.9932861328125
  },
  "isRightHanded": false,
  "resolution": {
    "width": 960,
    "height": 720
  },
  "queryImage": "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAA8AAAALQCAIAAADQFY7jAAAgAElEQVR4AaS9+5NdR5Lfh34BjW4AxJMgOTN8zCw5OzHriV2vvFrZDjtCVki2Xt5VaKVdybLClsL+3xz23+DQr9ZPlmO16xmvh"
}
{
  "poseFound": true,
  "position": {
    "x": -5.89516855615433,
    "y": 1.225031596452081,
    "z": 2.2112895596804227
  },
  "rotation": {
    "x": -0.007873432249486393,
    "y": 0.8212519784928444,
    "z": 0.03204363652415735,
    "w": 0.5696107462509017
  },
  "confidence": 0.46875,
  "mapIds": [
    "67e12d4bff7ecf561f2f8a0c"
  ],
  "mapCodes": [
    "MAP_RJFKKWQ1787J"
  ],
  "responseTime": 2572
}

Sample Response (JSON Body)

Query a VPS map or mapset using form-data

post
Authorizations
AuthorizationstringRequired
Bearer authentication header of the form Bearer <token>.
Body
mapCodestringOptional

The map code for the map to query (required if mapSetCode is not provided)

mapSetCodestringOptional

The map set code for the map set to query (required if mapCode is not provided)

queryModestring · enumOptional

Localization engine for this query. "vps-1" (default) is the fast standard engine (~2s). "vps-2" is a deep-search engine with up to 15% higher recall and improved accuracy, at higher latency (~3-4s). Ideal for offline or challenging scenes. Also supported on the multi-image query endpoint.

Default: vps-1Example: vps-2Possible values:
imageTypestring · enumOptional

Projection of the uploaded queryImage. "pinhole" (default) is a standard perspective photo, and fx, fy, px, py, width and height are required with it. "equirect" is a full 360 equirectangular panorama: camera intrinsics are not required and are ignored if sent, and the returned pose describes the forward-looking view, meaning the direction the centre column of the image faces. Works with both queryMode values.

Default: pinholeExample: equirectPossible values:
isRightHandedstring · enumOptionalExample: truePossible values:
fxstringOptional

Focal length in x, in pixels. Required when imageType is pinhole, ignored when it is equirect.

Example: 669.535888671875
fystringOptional

Focal length in y, in pixels. Required when imageType is pinhole, ignored when it is equirect.

Example: 669.535888671875
pxstringOptional

Principal point x, in pixels. Required when imageType is pinhole, ignored when it is equirect.

Example: 478.8777160644531
pystringOptional

Principal point y, in pixels. Required when imageType is pinhole, ignored when it is equirect.

Example: 364.9244079589844
widthstringOptional

Image width in pixels. Required when imageType is pinhole, ignored when it is equirect.

Example: 960
heightstringOptional

Image height in pixels. Required when imageType is pinhole, ignored when it is equirect.

Example: 720
queryImagestring · binaryRequired

Image file for multipart requests. JPEG or PNG, 30 MB or smaller. For pinhole, resolution must not exceed 1280x1280. For equirect, width must be 2048 to 16384 px with an aspect ratio of at least 1.9:1 (a 2:1 panorama).

convertToGeoCoordinatesstring · enumOptional

Convert result to geographic coordinates

Example: falsePossible values:
hintMapCodesstring[]Optional

List of map codes for hints (only valid with mapSetCode)

Example: ["MAP-X2P23E7Q35VD","MAP-Y3Q34F8R46WE"]
hintPositionstringOptional

Position hint "x,y,z" (comma-separated string). Must be in the map's left-handed (LHS / Unity) coordinate system, the same frame as the position field in a successful localization response (isRightHanded=false).

Example: 2.5,0.1,8.0
geoLocationstringOptional

Localize without naming a map. "latitude,longitude" in WGS 84 degrees. The nearest map whose geo-fence lies within geoSearchRadius (default 25m) is resolved and queried; if that map belongs to a map set, the whole set is queried. Distance is measured to the fence edge, so a point inside a fence is 0m. Only active maps with geoFenceReady=true are considered, and 404 is returned when nothing is in range. Mutually exclusive with mapId, mapCode, mapSetId and mapSetCode. It also doubles as geoHint when neither geoHint nor hintPosition is supplied, in which case hintRadius defaults to 100m rather than 25m, because a GPS fix is far less precise than a hint you supplied.

Example: 37.794853,-122.394573
geoSearchRadiusstringOptional

Overrides the geo-fence search radius in metres for this request only. Applies only when geoLocation is supplied, and is ignored otherwise. Falls back to 25m.

Example: 50
geoHintstringOptional

Geographic hint "latitude,longitude,altitude" (comma-separated). WGS 84 degrees for latitude and longitude. Altitude is an ELLIPSOIDAL height in metres (height above the WGS 84 ellipsoid), not mean sea level. Enable use2DFiltering to ignore altitude.

Example: 37.7749,-122.4194,10.0
hintRadiusstring · min: 5 · max: 100Optional

Search radius in meters for spatial filtering (default 25m). Only applies when geoHint or hintPosition is provided. Range 5-100.

Example: 25
use2DFilteringstring · enumOptional

When true, skip altitude (Y-axis) in geoHint spatial filtering. Only applies when geoHint is provided.

Example: falsePossible values:
hintFloorHeightstringOptional

JSON-encoded floor height band "[y_min, y_max]" in map-local coordinates. Search run within this vertical range. Order does not matter.

Example: [1.5, 4.5]
Responses
200

Query successful

application/json
poseFoundbooleanOptional

Indicates if the pose was successfully found

confidencenumberOptional
mapIdsstring[]Optional
mapCodesstring[]Optional
responseTimenumberOptional
post/vps/map/query-form
POST /v1/vps/map/query-form HTTP/1.1
Host: api.multiset.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 541

{
  "mapCode": "text",
  "mapSetCode": "text",
  "queryMode": "vps-2",
  "imageType": "equirect",
  "isRightHanded": "true",
  "fx": "669.535888671875",
  "fy": "669.535888671875",
  "px": "478.8777160644531",
  "py": "364.9244079589844",
  "width": "960",
  "height": "720",
  "queryImage": "binary",
  "convertToGeoCoordinates": "false",
  "hintMapCodes": [
    "MAP-X2P23E7Q35VD",
    "MAP-Y3Q34F8R46WE"
  ],
  "hintPosition": "2.5,0.1,8.0",
  "geoLocation": "37.794853,-122.394573",
  "geoSearchRadius": "50",
  "geoHint": "37.7749,-122.4194,10.0",
  "hintRadius": "25",
  "use2DFiltering": "false",
  "hintFloorHeight": "[1.5, 4.5]"
}
{
  "poseFound": true,
  "position": {
    "x": -2.8765866867008025,
    "y": 1.4018881843419664,
    "z": 7.677072632098843
  },
  "rotation": {
    "x": -0.0033476528966347096,
    "y": 0.6750939967230872,
    "z": -0.00310829178339555,
    "w": 0.7377175796541121
  },
  "confidence": 0.9175769612711023,
  "mapIds": [
    "67e12d4bff7ecf561f2f8a0c"
  ],
  "mapCodes": [
    "MAP_RJFKKWQ1787J"
  ],
  "responseTime": 2669
}

Sample Response (Form Data)

FormData Content-Type: When using fetch or similar HTTP clients with FormData, do not manually set the Content-Type header. The browser automatically sets it to multipart/form-data with the required boundary string. Manually setting it will strip the boundary and cause a parse error.

Code Example (Python)

VPS Multi Image Query API

Multi-image query API requires a minimum of 4 images in each request. Up to 6 images can be passed. Higher image counts increase localization robustness and accuracy but may compromise latency.

About image#_data properties: The image1_data, image2_data, etc. fields contain the local SLAM tracking data (position and rotation) for when each image was captured. This is the device pose in the local coordinate system from ARKit (iOS) or ARCore (Android) at the moment the image was taken.

Tracking poses are optional

The imageN_data parts are optional, which lets the multi-image query be used outside a SLAM session, for example from a set of stills or a camera rig with no tracking. Optional does not mean unnecessary: send them whenever you have them. A live ARKit or ARCore session already produces a pose per frame, and passing it gives the most accurate result.

Two rules:

  • Send a pose for every image, or for none. Without poses the images are matched against each other instead, so they must visually overlap. A partial set is not rejected, but it is treated exactly as if you had sent none, so it is worth making the choice explicit in your client.

  • A pose that you do send must be complete. All seven fields (x, y, z, qx, qy, qz, qw) must be present together, and the value must be valid JSON. Either problem fails with 400.

The trackingPose in the response is your input echoed back, so it is absent whenever the poses were not used.

Multi-image query for a VPS map or map set

post

Performs a query using several uploaded images, along with camera intrinsics and a map or map-set identifier. Requires a minimum of 4 images and accepts a maximum of 6 in a single request.

The request is multipart/form-data. The image binaries are sent as file parts named image1 to image6, and every other field, including each imageN_data tracking pose, is sent as a plain text part. The imageN_data parts are optional, but send them whenever you have them: they give the most accurate result. Send a tracking pose for every image, or for none of them. A pose sent for only some images is accepted but then not used, and the images must visually overlap each other, exactly as if you had sent none. A pose you do send must carry all seven fields and be valid JSON, or the request fails with 400.

Authorizations
AuthorizationstringRequired
Bearer authentication header of the form Bearer <token>.
Body
isRightHandedstring · enumOptional

Specifies whether the coordinate system is right-handed. Because this is form-data, it's sent as a string ("true" or "false").

Example: truePossible values:
widthstringRequired

The width (in pixels) of the input image(s).

Example: 960
heightstringRequired

The height (in pixels) of the input image(s).

Example: 720
pxstringRequired

The principal point x-coordinate.

Example: 478.838623046875
pystringRequired

The principal point y-coordinate.

Example: 365.346618652343
fxstringRequired

The focal length along x-axis.

Example: 670.4620971679688
fystringRequired

The focal length along y-axis.

Example: 670.4620971679688
mapCodestringOptional

Code to identify the map (required if mapSetCode is not provided).

mapSetCodestringOptional

A code to identify the map set.

convertToGeoCoordinatesstring · enumOptional

Convert result to geographic coordinates

Example: falsePossible values:
hintMapCodesstring[]Optional

List of map codes for hints (only valid with mapSetCode)

Example: ["MAP-X2P23E7Q35VD","MAP-Y3Q34F8R46WE"]
hintPositionstringOptional

Position hint "x,y,z" (comma-separated string). Must be in the map's left-handed (LHS / Unity) coordinate system — the same frame as the position field in a successful localization response (isRightHanded=false).

Example: 2.5,0.1,8.0
geoHintstringOptional

Geographic hint "latitude,longitude,altitude" (comma-separated). WGS 84 degrees for latitude and longitude. Altitude is an ELLIPSOIDAL height in metres (height above the WGS 84 ellipsoid), not mean sea level. Enable use2DFiltering to ignore altitude.

Example: 37.7749,-122.4194,10.0
hintRadiusstring · min: 5 · max: 100Optional

Search radius in meters for spatial filtering (default 25m). Only applies when geoHint or hintPosition is provided. Range 5-100.

Example: 25
use2DFilteringstring · enumOptional

When true, skip altitude (Y-axis) in geoHint spatial filtering. Only applies when geoHint is provided.

Example: falsePossible values:
hintFloorHeightstringOptional

JSON-encoded floor height band "[y_min, y_max]" in map-local coordinates. Search run within this vertical range. Order does not matter.

Example: [1.5, 4.5]
queryModestring · enumOptional

Localization engine. "vps-1" (default) is the standard engine. "vps-2" is the deep-search engine, slower but more accurate.

Default: vps-1Example: vps-1Possible values:
depthinteger · min: 1 · max: 5Optional

Widens how far the query searches inside a map, from 1 (default) to 5. Raise it on large maps. Higher values are slower.

Default: 1Example: 1
image1string · binaryRequired

The first image file to be uploaded.

image1_datastringOptional

Optional JSON-encoded tracking pose for image1: position x, y, z and rotation qx, qy, qz, qw.

Example: {"x":-5.1772,"y":0.2936,"z":-2.6439,"qx":-0.0185,"qy":0.9949,"qz":-0.0691,"qw":0.0703}
image2string · binaryOptional

The second image file to be uploaded.

image2_datastringOptional

Optional JSON-encoded tracking pose for image2: position x, y, z and rotation qx, qy, qz, qw.

Example: {"x":-3.12,"y":1.01,"z":2.56,"qx":0.0,"qy":0.707,"qz":0.0,"qw":0.707}
image3string · binaryOptional

The third image file to be uploaded.

image3_datastringOptional

Optional JSON-encoded tracking pose for image3: position x, y, z and rotation qx, qy, qz, qw.

Example: {"x":1.23,"y":-0.56,"z":5.0,"qx":-0.0185,"qy":0.9949,"qz":-0.0691,"qw":0.0703}
image4string · binaryOptional

The fourth image file to be uploaded.

image4_datastringOptional

Optional JSON-encoded tracking pose for image4: position x, y, z and rotation qx, qy, qz, qw.

Example: {"x":10.0,"y":-2.0,"z":0.0,"qx":0.0,"qy":1.0,"qz":0.0,"qw":0.0}
Responses
200

Query successful

application/json
poseFoundbooleanOptional
imageIdstringOptional
mapIdsstring[]Optional
confidencenumberOptional
mapCodesstring[]Optional
responseTimenumberOptional
post/vps/map/multi-image-query
POST /v1/vps/map/multi-image-query HTTP/1.1
Host: api.multiset.ai
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 929

{
  "isRightHanded": "true",
  "width": "960",
  "height": "720",
  "px": "478.838623046875",
  "py": "365.346618652343",
  "fx": "670.4620971679688",
  "fy": "670.4620971679688",
  "mapCode": "",
  "mapSetCode": "",
  "convertToGeoCoordinates": "false",
  "hintMapCodes": [
    "MAP-X2P23E7Q35VD",
    "MAP-Y3Q34F8R46WE"
  ],
  "hintPosition": "2.5,0.1,8.0",
  "geoHint": "37.7749,-122.4194,10.0",
  "hintRadius": "25",
  "use2DFiltering": "false",
  "hintFloorHeight": "[1.5, 4.5]",
  "queryMode": "vps-1",
  "depth": 1,
  "image1": "binary",
  "image1_data": "{\"x\":-5.1772,\"y\":0.2936,\"z\":-2.6439,\"qx\":-0.0185,\"qy\":0.9949,\"qz\":-0.0691,\"qw\":0.0703}",
  "image2": "binary",
  "image2_data": "{\"x\":-3.12,\"y\":1.01,\"z\":2.56,\"qx\":0.0,\"qy\":0.707,\"qz\":0.0,\"qw\":0.707}",
  "image3": "binary",
  "image3_data": "{\"x\":1.23,\"y\":-0.56,\"z\":5.0,\"qx\":-0.0185,\"qy\":0.9949,\"qz\":-0.0691,\"qw\":0.0703}",
  "image4": "binary",
  "image4_data": "{\"x\":10.0,\"y\":-2.0,\"z\":0.0,\"qx\":0.0,\"qy\":1.0,\"qz\":0.0,\"qw\":0.0}"
}
{
  "poseFound": true,
  "estimatedPose": {
    "position": {
      "x": 3.9023228363353613,
      "y": 2.2199969114542415,
      "z": 7.684019738005462
    },
    "rotation": {
      "x": 0.0008889080606250241,
      "y": 0.7454695784085924,
      "z": -0.022682644709609446,
      "w": 0.6661529967948453
    }
  },
  "trackingPose": {
    "position": {
      "x": 0.0022450201213359833,
      "y": 2.471872329711914,
      "z": -10.018059730529785
    },
    "rotation": {
      "x": 0.030655404552817345,
      "y": 0.14812710881233215,
      "z": -0.00305502163246274,
      "w": -0.9884883761405945
    }
  },
  "imageId": "image4",
  "mapIds": [
    "67e12d4bff7ecf561f2f8a0c"
  ],
  "confidence": 0.34274043817304123,
  "frames": [
    {
      "imageId": "image1",
      "poseFound": true,
      "position": {
        "x": 3.840479122718551,
        "y": 2.235871409437739,
        "z": 7.531184729001473
      },
      "rotation": {
        "x": 0.0104227310558921,
        "y": 0.7218904471209736,
        "z": -0.0248105549134402,
        "w": 0.6914338805274115
      },
      "confidence": 0.2988120487183476
    },
    {
      "imageId": "image2",
      "poseFound": true,
      "position": {
        "x": 3.8697402118840367,
        "y": 2.228145503710395,
        "z": 7.601552884101918
      },
      "rotation": {
        "x": 0.0061140925713855,
        "y": 0.7331886201553348,
        "z": -0.0235510983247741,
        "w": 0.6795726114402537
      },
      "confidence": 0.31204558839107516
    },
    {
      "imageId": "image3",
      "poseFound": false
    },
    {
      "imageId": "image4",
      "poseFound": true,
      "position": {
        "x": 3.9023228363353613,
        "y": 2.2199969114542415,
        "z": 7.684019738005462
      },
      "rotation": {
        "x": 0.0008889080606250241,
        "y": 0.7454695784085924,
        "z": -0.022682644709609446,
        "w": 0.6661529967948453
      },
      "confidence": 0.34274043817304123
    }
  ],
  "mapCodes": [
    "MAP_RJFKKWQ1787J"
  ],
  "responseTime": 4919
}

Sample Response (Multi Image)

Per-image poses (frames)

Alongside the single estimatedPose, the response carries a frames array with one entry per image you sent, in the order the images were numbered. Each entry reports whether that individual image localized on its own, and if it did, the 6-DoF pose computed from it.

Field
Type
Description

imageId

string

Which image this entry describes (image1 to image6), matching the file part you uploaded.

poseFound

boolean

Whether this individual image produced a pose.

position

object

x, y, z in map-local coordinates. Present only when poseFound is true.

rotation

object

Quaternion x, y, z, w. Present only when poseFound is true.

confidence

number

Confidence score for this image alone. May be absent on a frame that did not localize.

How frames relates to the top-level pose:

  • estimatedPose remains the answer to use. It is the consensus pose across all images and is more robust than any single frame.

  • The top-level imageId names the winning frame, so the entry with that imageId carries the same position, rotation, and confidence as estimatedPose.

  • Every pose in frames is in the same coordinate frame as estimatedPose: it follows the isRightHanded value you sent, and on a versioned map it is expressed in the base map's frame.

  • Individual frames can fail while the overall query succeeds. A frame with "poseFound": false has no position or rotation, which is normal when one image in the set is blurred, occluded, or pointed at a featureless surface.

  • frames is informational. It is useful for diagnosing capture quality, spotting outlier viewpoints, and understanding which frames drove the result, but you do not need it for standard localization.

FormData Content-Type: When using fetch or similar HTTP clients with FormData, do not manually set the Content-Type header. The browser automatically sets it to multipart/form-data with the required boundary string. Manually setting it will strip the boundary and cause a parse error.

Code Example (Python)

Split the request in two parts: the image binaries go in files, and every other field, including each imageN_data tracking pose, goes in data as a string.

Rules for the multipart body:

  • File parts must be named image1 to image6, and each one needs a matching imageN_data text part with the same number. A missing imageN_data returns 400 with Missing metadata for imageN.

  • Each imageN_data value is a JSON-encoded string containing x, y, z, qx, qy, qz and qw. All seven keys are required.

  • Send between 4 and 6 images. Fewer returns At least 4 image file is required!, more returns Maximum 6 image files allowed!.

  • Pass exactly one of mapCode or mapSetCode.

  • Do not set the Content-Type header yourself. requests adds multipart/form-data with the boundary when you pass files.

Query Parameters

Every parameter below is optional, and all of them apply to the query endpoints above. Omit them and the query still runs.

For the remaining localization parameters, geoHint, hintRadius, use2DFiltering and hintMapCodes, see Localization.

Spatial Hint: hintPosition

The hintPosition parameter restricts the localization search to a radius around a given point in the map, speeding up the query and improving accuracy in visually repetitive scenes.

Parameter
Type
Description

hintPosition

[x, y, z]

Hint point in the map's left-handed (LHS / Unity) coordinate system

hintRadius

number

Search radius in meters (default 25, range 5–100)

hintPosition is in LHS (Unity) coordinates, the same coordinate system returned in the position field of a successful localization response (isRightHanded: false). A previous localization result's position can be passed directly as the hint. If your application works in right-handed space (e.g. ROS, Three.js), convert to LHS before sending.

On form-data endpoints, pass hintPosition as a JSON-encoded string, e.g. "[2.5, 0.1, 8.0]". See Pose Prior : HintPosition for the full guide.

Floor-Level Search: hintFloorHeight

The hintFloorHeight parameter limits the search to a specific vertical band, enabling floor-level localization in multi-floor buildings.

Parameter
Type
Description

hintFloorHeight

[y_min, y_max]

Vertical band in map-local Y coordinates

Rules:

  • Both values are in map-local coordinates (or global MapSet coordinates for MapSet queries)

  • Order does not matter: [-3, -1] and [-1, -3] both select images with y ∈ [-3, -1]

  • Can be combined with hintPosition: spatial filter runs first, height filter applies on the result

Examples:

Query Mode: queryMode

The queryMode parameter selects which localization engine runs your query, letting you trade latency for accuracy. The request and response format stay exactly the same on both engines.

Value
Engine
Description

vps-1

Standard (default)

The fast standard localization engine, roughly 1 second for a single-frame query and 2 to 4 seconds for a multi-image query. Best for real-time, interactive localization.

vps-2

Deep Search

A deep-search engine with up to 15% higher recall and improved accuracy, at higher latency (around 2 seconds for a single-frame query, around 5 seconds for a multi-image query). Best for offline or background workflows and challenging, visually repetitive scenes.

Rules:

  • Optional. When omitted, the query runs on vps-1, so existing integrations are unaffected.

  • Supported on the single-image endpoints, /vps/map/query (JSON) and /vps/map/query-form (form-data), including imageType=equirect, and on the multi-image endpoint, /vps/map/multi-image-query.

  • Can be combined with all localization parameters (hintPosition, hintRadius, hintFloorHeight, geoHint, hintMapCodes).

  • Works with Maps, MapSets, and versioned maps.

Examples:

Use vps-2 when accuracy matters more than latency, for example when placing persistent content or localizing in repetitive corridors. For high-frequency relocalization during an AR session, vps-1 remains the recommended default. You can also try both engines on your own datasets from the Developer Portal simulation viewer. See Query Mode for guidance on choosing between the two.

Search Depth: depth

depth widens how far the query searches inside a map before it settles on a pose. Raise it on large maps and wide open spaces, where the right part of the space is harder to find.

Value
Search

1

Default. Suits most maps.

2 to 5

Progressively wider. Useful on large venues.

Rules:

  • Optional. An integer from 1 to 5, defaulting to 1, so existing integrations are unaffected.

  • Supported on the single-image endpoints, /vps/map/query (JSON) and /vps/map/query-form (form-data), and on the multi-image endpoint, /vps/map/multi-image-query.

  • Applies to both pinhole and equirect queries, and to both queryMode values.

  • A wider search takes longer, so raise it only as far as you need.

  • Works with Maps, MapSets, and versioned maps, and combines with the other localization parameters.

Example:

Start at the default. Raise depth only if a large map returns no pose, or a pose you do not expect. On small and medium maps it makes no practical difference and only costs time.

Localize by Coordinate: geoLocation

geoLocation localizes without naming a map. Send a position and the nearest map whose geo-fence is in range is resolved and queried for you.

This only works on geo-referenced maps. A map resolves by coordinate only once it has a geo-fence, and it only gets a fence once it has real-world coordinates and a heading. If a map you expect is never matched, that is almost always why. See Geo-fence for how to geo-reference one.

Parameter
Meaning

geoLocation

[latitude, longitude] in WGS 84 degrees. Mutually exclusive with mapId, mapCode, mapSetId and mapSetCode.

geoSearchRadius

Overrides the search radius in metres for this request only. Ignored unless geoLocation is supplied. Defaults to 25 m.

Rules:

  • Only active maps in your account with geoFenceReady: true are considered.

  • Distance is measured to the fence edge, so a point inside a fence is 0 m away.

  • If the resolved map belongs to a MapSet, the whole set is queried, which is what you want indoors.

  • When nothing is in range the request returns 404.

A successful response carries resolvedFrom, naming the map the coordinates landed on:

geoLocation doubles as a geoHint. If you supply neither geoHint nor hintPosition, the coordinate is reused as the localization prior, and hintRadius then defaults to 100 m rather than the usual 25 m, because a raw GPS fix is less precise than a hint you calculated yourself.

Resolving by coordinate costs a spatial lookup on every request. For anything running at frame rate, call GET /v1/vps/map/nearby once, cache the code it returns, and query that instead. See Geo-fence.

Image Type: imageType

imageType tells the query which projection your image uses. It applies to /vps/map/query-form only.

Value
Image
Camera intrinsics

pinhole

A standard perspective photo (default)

Required. Send fx, fy, px, py, width, height.

equirect

A full 360° equirectangular panorama

Not required. Send them and they are ignored.

A pinhole query needs intrinsics before a pixel can become a direction. An equirectangular image carries that already, so there is nothing to send. You get back one pose: the pose of the forward-looking view, meaning the direction the centre column of the image faces.

Rules:

  • Optional. When omitted the query runs as pinhole, so existing integrations are unaffected.

  • Works with both queryMode values. queryMode=vps-2 runs the panorama on the deep-search engine.

  • queryImage must be 2048 to 16384 px wide with an aspect ratio of at least 1.9:1, and 30 MB or smaller. Outside that, the request fails with 400, or 413 if it is only the file size.

  • Works with Maps, MapSets, and versioned maps, and with all localization parameters.

  • REST only. The Unity, Quest, iOS and Android SDKs capture perspective frames and do not expose imageType.

Example:

The response has the same shape as a pinhole query: poseFound, position, rotation, confidence, and the matched mapIds and mapCodes. The rotation describes the forward-looking view, so orient your panorama with its centre column along your direction of travel if you want the returned heading to mean that. See Equirect Query.

Because one panorama covers the whole horizon, an equirect query does not depend on the user facing a mapped surface, which makes it a good fit for tripod, trolley, and robot captures. For a hand-held AR session, a pinhole frame from the device camera is still the right choice.

PreviousAuthentication
NextOSCP GeoPose Protocol

Last updated

Was this helpful?