Skip to main content
This node converts a depth map from a DA3_GEOMETRY object into a 3D point cloud. It applies filtering based on confidence and sky masks, and transforms the points into a common world coordinate system suitable for multi-view scenes.

Inputs

ParameterDescriptionData TypeRequiredRange
da3_geometryThe DA3_GEOMETRY object containing depth data and optional image, confidence, and sky mapsDA3_GEOMETRYYes-
batch_indexWhich image of a batch to convert (default: 0)INTYes0 to 4096
confidence_thresholdExclude pixels whose per-image normalised confidence is below this value (0 = keep all). Used when the geometry has a confidence map (Small/Base models). (default: 0.1)FLOATYes0.0 to 1.0
use_sky_maskExclude sky-probability pixels (sky >= 0.5). Used when the geometry has a sky map (Mono/Metric models). (default: True)BOOLEANYesTrue or False
downsampleTake every Nth pixel (1 = full resolution). Higher values give fewer points and faster processing. (default: 1)INTYes1 to 16

Outputs

Output NameDescriptionData Type
point_cloudA point cloud object containing filtered 3D points, optional colors, and optional confidence valuesDA3_POINT_CLOUD
This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 3cf5bdbb8afdfcfc02f9832a8cbc5a3df49da755dea6df01792aa6ef9e5d7287