A 612M-point industrial MEP TLS dataset and cross-paradigm benchmark show best supervised mIoU of 55.74% versus 15.79% zero-shot Point-SAM, a 39.95-point domain gap from 215:1 imbalance and cylindrical ambiguity.
Computing in Civil Engineering 33, 66–73
1 Pith paper cite this work, alongside 61 external citations. Polarity classification is still indexing.
1
Pith paper citing it
61
external citations · external index
fields
cs.CV 1years
2026 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Industrial3D: A Water-Treatment TLS Point Cloud Dataset and Cross-Paradigm Benchmark for MEP Scene Understanding
A 612M-point industrial MEP TLS dataset and cross-paradigm benchmark show best supervised mIoU of 55.74% versus 15.79% zero-shot Point-SAM, a 39.95-point domain gap from 215:1 imbalance and cylindrical ambiguity.