Zero-Shot 3D Affordance Mapping

Geometry-aware  ·  Evaluated on LASO benchmark

Scene
Preloaded scene
Affordance query Method
Points
High-score
Time
Upload your own
Point cloud (.npy, .ply, or .pkl)
Loading…
Drag to rotate  ·  Scroll to zoom
High Mid Low
Method comparison Top-down · same scene · same query · hover cards for explanation
CLIP only
?
CLIP only (baseline) Lifts 2D patch features into 3D, scores by text similarity. Finds semantically similar-looking regions but ignores surface geometry — a flat table can score as high as a graspable handle.
Geometry only
?
Geometry only Scores points by local surface shape — planarity, normal consistency, curvature — matched to the query's physical requirements. No visual or language understanding; misses semantic context.
Geometry-aware ours
?
Geometry-aware (ours) Multiplies CLIP and geometry scores. A point must look right AND be shaped right — suppressing CLIP false positives and producing tighter, physically plausible regions. Best IoU on LASO benchmark.
What to look for: our method produces a tighter yellow cluster on the correct affordance region. CLIP-only spreads scores broadly; geometry-only can miss the right object entirely.