Drop CMM point CSVs and the nominal glTF mesh on the canvas, best-fit align them, and compute point-to-surface deviation with live tolerance sliders. Deliver a color-mapped glTF deviation model plus a per-part pass/fail report.
The CMM spits out a CSV of measured points per part. The nominal lives in CAD. The software that compares them is a licensed seat bolted to one PC in the quality lab, and its output is a 40-page PDF nobody opens. When a supplier asks where exactly the part is out, you end up emailing screenshots.
LSD treats the measurement table and the CAD mesh as equal citizens. Points are rows, the mesh is geometry, and both drop onto the same canvas and meet in the 3D viewer. Because every step is a live node, alignment quality and tolerance choices are things you see, not parameters you commit to blind — change the tolerance and the model repaints before you let go of the slider. The deliverable is just as portable as the pipeline is interactive, since the deviation map travels as a single glTF.
Any CMM export with XYZ coordinates works — Zeiss Calypso, Mitutoyo, PC-DMIS, or a homegrown CSV. Export the nominal as glTF from your CAD tool; most do it natively now. The sample project uses 24 parts at roughly 500 points each, and the full pipeline re-runs in under two seconds thanks to cached intermediates.
Drag the folder of CMM CSVs onto the canvas and an @load node appears with every file batched into one table. LSD sniffs the columns — part ID, feature, and measured XYZ — and previews the first rows. Nothing to configure yet; the raw point cloud already renders in the 3D viewer.
Drop the part's glTF export next to it. A second @load node appears and the nominal surface renders in the 3D viewer, with the measured points floating nearby in machine coordinates. The mismatch is obvious — that is exactly what alignment fixes.
Add an @shape alignment step and pick best-fit registration. The solver snaps the measured points onto the nominal mesh and reports an RMS residual per part. Toggle datum-based alignment instead if your drawing calls one out — the preview re-renders either way.
Chain a deviation step. Every point gets a signed distance to the nearest mesh surface, and a histogram of deviations appears in the step's preview. Drag the tolerance sliders — say ±0.05 mm — and points re-classify to pass, warn, or fail instantly.
Add an @deliver node set to glTF. The nominal mesh is baked with a blue-to-red deviation map and exported as one portable file. Anyone can spin it in a browser viewer — no metrology software needed.
Add a report delivery next to it. It pulls per-feature stats, worst offenders, and deviation snapshots into a per-part pass/fail PDF. Run tomorrow's measurements through the same canvas and the report regenerates from cached intermediates in seconds.
Batch CMM measurement CSVs and the nominal CAD mesh into one canvas.
Best-fit points to the surface and compute signed point-to-surface deviation against live tolerances.
Export a color-mapped glTF deviation model and a per-part pass/fail report.
Resample a week of machine sensor logs, baseline each tag, and flag drift and step changes on a live dashboard with a ranked maintenance shortlist.
Model post-closure pit-lake rebound in LSD — krige borehole heads against a NetCDF recharge grid and deliver a live 3D drawdown model plus report.
Validate 63 LAS drillhole logs against collar surveys, krige a lithology block model, and export one glTF the whole team can open.
Build churn features from Postgres events and Parquet snapshots, catch a leaky window visually, and score the holdout with ONNX — on one canvas.
Score a million-row Parquet batch with an ONNX model — training-identical normalization, live previews, scored Parquet and metrics out.
Turn raw LAS/LAZ sweeps from a mobile robot into a nav-ready occupancy grid and 3D map — registration to export with zero scripts.
Sync CSV sensor logs with live REST telemetry, flag outliers and dropouts, and score every robot pass/fail before the field trial.
Turn folders of line-scan images and a label CSV into an ONNX defect-segmentation pipeline with overlay QA and a per-coil defect report.
Turn GeoTIFF orthomosaics into a stitched land-cover raster with per-class area stats, using tiled ONNX segmentation you can preview at every step.
Join a live meter feed to 85 campus building meshes, aggregate it hourly, and paint a 3D heat-map that repaints as energy use shifts, plus a weekly report.
Calibrate live strain telemetry, place gauges on the bridge mesh from a CSV, and color the structure by stress live — plus an alert log on every exceedance.
Turn a CT DICOM series into an ONNX organ segmentation you QA in 3D, then export an annotated volume and a per-organ volumetrics report.
Drag the folder of CMM CSVs onto the canvas and an @load node appears with every file batched into one table. LSD sniffs the columns — part ID, feature, and measured XYZ — and previews the first rows. Nothing to configure yet; the raw point cloud already renders in the 3D viewer.
Add an @shape alignment step and pick best-fit registration. The solver snaps the measured points onto the nominal mesh and reports an RMS residual per part. Toggle datum-based alignment instead if your drawing calls one out — the preview re-renders either way.
Chain a deviation step. Every point gets a signed distance to the nearest mesh surface, and a histogram of deviations appears in the step's preview. Drag the tolerance sliders — say ±0.05 mm — and points re-classify to pass, warn, or fail instantly.
Add an @deliver node set to glTF. The nominal mesh is baked with a blue-to-red deviation map and exported as one portable file. Anyone can spin it in a browser viewer — no metrology software needed.