Lidar Data Requirements

By organizing LiDAR data into a single JSON file, you can quickly import all required reconstruction data into MipMap Desktop with one click, or merge it with reconstruction parameters and pass it to the MipMap SDK for fully automatic textured model and Gaussian splatting reconstruction.

For easier distinction, the JSON file extension should be changed to .mpl before importing into MipMap Desktop (for example, mipmap_lidar.mpl).

Required data includes:

• ✅ Point Cloud Data: Usually point cloud data in LAS format, with timestamps recorded in the gps_time field at acquisition time
• ✅ Image Data: Image collection, including each image path, timestamp, position and attitude angle (optional), etc.
• ✅ Camera Parameters: Camera focal length, principal point internal parameters, and distortion parameters

LIDAR Reconstruction Parameters

Parameter Name	Type	Required	Description
coordinate_system	JSON	Yes	Coordinate system of image POS, see coordinate_system for details
camera_meta_data	JSON	Yes	Camera parameters, see camera_meta_data for details
image_meta_data	JSON	Yes	Image collection, see image_meta_data for details
lidar_data	JSON	Yes	Lidar data, see lidar_data for details

coordinate_system Object

Field Name	Type	Description	Example Value
type	int	Coordinate system type: 0=LocalENU, 1=Local, 2=Geographic, 3=Projected, 4=ECEF	2
type_name	string	Coordinate system type name (optional, auxiliary description)	"Geographic"
label	string	Coordinate system name (optional)	"WGS 84"
epsg_code	int	EPSG code (required for geographic/projected/geocentric coordinate systems)	4326
wkt	string	WKT string (optional, alternative to epsg_code)	"..."
origin_point	array[3]	Origin WGS84 coordinates [longitude, latitude, elevation] (required only when type=0 LocalENU)	[114.12, 22.12, 0]
offset	array[3]	Coordinate system origin offset (optional)	[0, 0, 0]

Below are the most common WGS84 and CGCS2000 coordinate systems:

{
  "type": 2,              // 0=LocalENU, 1=Local, 2=Geographic, 3=Projected
  "type_name": "Geographic",
  "label": "WGS 84",     // Coordinate system name
  "epsg_code": 4326      // EPSG code
}
{
  "type": 3,              // 0=LocalENU, 1=Local, 2=Geographic, 3=Projected
  "type_name": "Projected",
  "label": "WGS 84 / UTM zone 50N",     // Coordinate system name
  "epsg_code": 32650      // EPSG code
}
{
  "type": 2,              // 0=LocalENU, 1=Local, 2=Geographic, 3=Projected
  "type_name": "Geographic",
  "label": "CGCS2000",     // Coordinate system name
  "epsg_code": 4490      // EPSG code
}
{
  "type": 2,              // 0=LocalENU, 1=Local, 2=Geographic, 3=Projected
  "type_name": "Projected",
  "label": "CGCS2000 / 3-degree Gauss-Kruger CM 114E",     // Coordinate system name
  "epsg_code": 4547      // EPSG code
}

camera_meta_data Object

Field Name	Type	Required	Description
id	int	Yes	Camera unique ID
meta_data	object	Yes	Camera metadata, see table below

meta_data sub-field description:

Field Name	Type	Required	Description
projection_model	int	Yes	Lens model: 0-perspective lens (k1,k2,k3,p1,p2); 1-fisheye lens (k1,k2,k3,k4)
camera_name	string	Yes	Camera name
width	int	Yes	Sensor width (pixels)
height	int	Yes	Sensor height (pixels)
parameters	array	Yes	Camera internal parameter group (perspective camera order: fx, fy, cx, cy, k1, k2, k3, p1, p2; fisheye camera order: fx fy cx cy k1 k2 k3 k4)
constant_parameters	array	No	Array of parameter indices to fix camera internal parameters during AT solution, specified according to the parameter order in parameters (index starts from 0), e.g., for perspective camera, specifying [0,1,2,3,4,5,6,7,8] means fixing all parameters
mask_path	string	No	Path to the binary mask image in PNG format. Pixel regions with value 0 are ignored during reconstruction processing (the mask is applied to all images captured by this camera)

Typical use case for a camera mask: when a fixed camera is mounted on a robot and the lens can capture parts of the robot body, you can use a mask to ignore those pixel regions during reconstruction.

Perspective lens
"camera_meta_data": [
  {
    "id": 1,
    "meta_data": {
      "projection_model": 0,    // Perspective camera
      "camera_name": "common",
      "width": 5280,
      "height": 3956,
      "parameters": [
        3713.29,                // fx
        3713.29,                // fy
        2647.02,                // cx
        1969.28,                // cy
        -0.11257524,            // k1
        0.01487443,             // k2
        -0.00008572,            // k3
        1e-7,                   // p1
        -0.02706411             // p2
      ]
    }
  }
]
Fisheye lens
"camera_meta_data": [
  {
    "id": 1,
    "meta_data": {
      "camera_name": "fisheye",         // Fisheye camera
      "projection_model": 1,
      "width": 3600,
      "height": 3600,
      "parameters": [
        982.7593599212141,              // fx
        982.7593599212141,              // fy
        1747.6373897301492,             // cx
        1806.4116030074354,             // cy
        0.03702410479839055,            // k1
        -0.016007338300982825,          // k2
        -1.0884582901480562e-05,        // k3
        -9.773097281093723e-05          // k4
      ]
    }
  }
]

image_meta_data Object

Field Name	Type	Required	Description
id	int	Yes	Image unique ID
path	string	Yes	Image absolute path
meta_data	object	Yes	Image metadata, see table below

meta_data sub-field description:

Field Name	Type	Required	Description
width	int	Yes	Image width (pixels)
height	int	Yes	Image height (pixels)
camera_id	int	Yes	Corresponding camera ID
timestamp	double	Yes	Timestamp of image acquisition time; must match the time recorded in the gps_time field of the LAS point cloud. When this attribute is set, trajectory data is not required
pos	array[3]	Yes	POS position [longitude/X, latitude/Y, elevation/Z]
pos_sigma	array[3]	Yes	POS position accuracy: centimeter-level RTK [0.03,0.03,0.06]; decimeter-to-meter level [0.5,0.5,1]; meter level and above [2.0,2.0,5.0]. LIDAR data recommends centimeter-level accuracy
orientation	array[9]	No	3x3 rotation matrix (9 values, row-major, unit vectors, world to camera). Strongly recommended to specify for fisheye images
position_constant	bool	No	Whether to fix position (true/false); fixed position means AT will not optimize or change image position, keeping input values
mask_path	string	No	Path to the binary mask image in PNG format. Pixel regions with value 0 are ignored during reconstruction processing

Tip: binary mask images are used to mark invalid regions. The SDK ignores invalid regions during reconstruction to improve efficiency and obtain cleaner results.

lidar_data Data

Field Name	Type	Description
coordinate_system	JSON	Coordinate system definition for lidar data
laser_meta_data	array	List of lidar point cloud file metadata

laser_meta_data Sub-fields

Field Name	Type	Description
id	int	LAS point cloud data ID
path	string	LAS point cloud file path (supports LAS format)

Example:

{
  "coordinate_system": {
    "type": 2,
    "epsg_code": 4326
  },  
  "camera_meta_data": [
  {
    "id": 1,
    "meta_data": {
      "camera_name": "Left",
      "projection_model": 1,
      "width": 3600,
      "height": 3600,
      "parameters": [
        982.7593599212141,
        982.7593599212141,
        1747.6373897301492,
        1806.4116030074354,
        0.03702410479839055,
        -0.016007338300982825,
        -1.0884582901480562e-05,
        -9.773097281093723e-05
      ]
    }
  },
  {
    "id": 2,
    "meta_data": {
      "camera_name": "Right",
      "projection_model": 1,
      "width": 3600,
      "height": 3600,
      "parameters": [
        982.7593599212141,
        982.7593599212141,
        1747.6373897301492,
        1806.4116030074354,
        0.03702410479839055,
        -0.016007338300982825,
        -1.0884582901480562e-05,
        -9.773097281093723e-05
      ]
    }
  }
  ],
  "image_meta_data":[
    {
        "id": 1,
        "path": "\\left\\2390-195042-472_00395-L.JPG",
        "meta_data": {
        "width": 3600,
        "height": 3600,
        "camera_id": 1,
        "timestamp": 1.0000,
        "pos": [
            -2272303.077314121,
            5011055.355739306,
            3215292.943560472
        ],
        "pos_sigma": [0.03,0.03,0.06],
        "orientation": [
            0.8929275412022056,
            0.43070972182403255,
            0.13103259781004117,
            -0.4500241512548592,
            0.8457917052937085,
            0.2865565468519331,
            0.012596406230632032,
            -0.31484206641207435,
            0.9490604847782084
        ]
        }
    },
    {
        "id": 2,
        "path": "\\right\\2390-195042-472_00395-R.JPG",
        "meta_data": {
        "width": 3600,
        "height": 3600,
        "camera_id": 2,
        "timestamp": 2.0000,
        "pos": [
            -2272303.117693735,
            5011055.368901664,
            3215292.967908075
        ],
        "pos_sigma": [0.03,0.03,0.06],
        "orientation": [
            0.8918935649712837,
            0.435497387453275,
            0.12193397510204676,
            -0.4504120798442928,
            0.8311302214603127,
            0.3261157973874772,
            0.040679566039387514,
            -0.34578111645476495,
            0.9374329802231962
        ]
        }
    }
  ],
  "lidar_data": {
    "coordinate_system": {
      "type": 3,
      "epsg_code": 32632
    },
    "laser_meta_data": [            // Lidar point cloud file list
      {
        "id": 1,                    // File ID
        "path": "C:/path/to/file1.las"  // Point cloud file path
      },
      {
        "id": 2,                    // File ID
        "path": "C:/path/to/file2.las"  // Point cloud file path
      }
    ]
  }
}