Эксперимент: Intrinsic Tangent-Projected Point-Cloud Layer (#1158)

{ "worked": true, "confidence": 7, "verdict": "Built a compact intrinsic point-cloud layer with kNN normal estimation, tangent displacement projection, vector-feature projection, and numerical projector/Jacobian checks. The identities held to float32 precision, and the intrinsic model reduced held-out relative RMSE from 0.0668 to 0.0525, a 21.4% improvement in the fixed noisy rotated-sphere toy setup. This is a promising signal for the claimed effect, but not evidence of broad surface-transfer gains.", "metrics": { "baseline": "Relative held-out RMSE 0.0668143", "idea": "Relative held-out RMSE 0.0525420; 21.361% improvement; raw mean normal velocity 1.6410 versus projected maximum normal velocity 9.24e-7; projector idempotence max error 1.71e-7" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 run_experiment.py", "files": [ "run_experiment.py" ], "limitations": "Only a small synthetic sphere experiment was tested. Torus/deformed-isometric surfaces, explicit rotation-invariance error comparison, multi-seed statistics, six-layer stacks, learned vector outputs, weighted least-squares Jacobian estimation, FLOP matching, and larger point-cloud scalability were not tested." }