Segment 3D

Manual and semi-automated segmentation of 3D spatial data — point clouds and meshes — into named, coloured classes, for building ML training sets and for review/QA of existing labels. Drop a PCD/XYZ/PTS cloud or an OBJ/STL/PLY/3MF/STEP/IGES model. Select with rectangle, polygon or lasso, or click a seed point and grow the region outwards (kNN neighbours on clouds, triangle-edge adjacency on meshes); shrink to erode a ragged boundary. Type a class name, pick its colour, and label the selection — each labelled segment becomes a coloured group under Features in the object tree, with per-segment and per-class show/hide, recolour and delete. Section planes cut into dense clouds to reach interiors. Export the labels as a dense per-element CSV (one row per point/face with class id and coordinates) or as a sparse JSON class/segment manifest, and export the geometry alongside it so the pair forms a complete dataset.

Supported file formats: PCD, XYZ, PTS, OBJ, STL, PLY, 3MF, STEP, STP, IGES, IGS, X3D