Automated Recognition of Unlabeled Items in BIM Models
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
In early stages of fast tracked construction projects—such as mega industrial projects—contractors do not have access to detailed and final drawings. Yet, they usually need rough estimates of material quantities in the project. They usually depend on initial versions of BIM models that contain all trades (e.g., pipes, steel, etc.) information. Because they are premature models, 3D object attributes may be missed, omitted, inconsistent, or incomplete which makes extracting quantities from them a manual, time-consuming, and inaccurate task. In this research, we aim to automate this task by applying shape recognition techniques on unlabeled 3D models. These techniques have been used in different fields such as handwriting recognition, object recognition, and 3D object search and retrieval. We experiment with some of these techniques to estimate material quantities for industrial construction projects based on the geometry of unlabeled 3D objects. We investigate a number of these techniques keeping in mind that the main usage will be a preliminary estimate in early stages of the project; therefore, we favor fast techniques with a margin of error over more accurate—but relatively slow—ones. This paper discusses applicability of these techniques and shows the results of applying and testing them on real industrial construction projects from a partner contractor.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it