Integrating Inverse Photogrammetry and a Deep Learning–Based Point Cloud Segmentation Approach for Automated Generation of BIM Models
Bibliographic record
Abstract
Automatically converting three-dimensional (3D) point clouds into building information modeling (BIM) has been an active research area over the past few years. However, existing solutions in the literature have been suffering the limitations of covering all different design scenarios (prior knowledge-based approach) or collecting sufficient point clouds as training data sets (3D deep learning–based approach). To tackle this issue, we propose a fused system to automatically develop as-built BIMs from photogrammetric point clouds. A series of images is captured to generate a high-quality point cloud, which is then preprocessed by removing noise and downsizing points. Meanwhile, a two-dimensional (2D) deep-learning method, DeepLab, is utilized to semantically segment elements (e.g., walls, slabs, and columns) from the collected images. Subsequently, an inverse photogrammetric pipeline is employed to recognize element categories in the point cloud by projecting the isolated 3D planes into 2D images and assigning the identified elements to the 3D planes. Finally, the industry foundation classes are devised to create as-built BIMs based on the segmented point clouds. In order to evaluate the performance of the proposed system, we selected six cases with various elements as the testbed. The prospective results reveal that (1) our system can provide a highly automated solution to develop as-built BIMs; and (2) 39 out of 45 elements in six different cases are successfully recognized in point clouds.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".