The paper introduces an adaptive region‑dividing strategy that projects a 3D point cloud onto a bird’s‑eye‑view plane to detect building regions, then back‑projects bounding boxes to create structure‑aligned training blocks for unified scene‑level evaluation. It also proposes a fine‑grained classification model using a point transformer classifier and a spatially‑supervised contrastive loss to improve inter‑class discriminability, addressing class imbalance with a weighted cross‑entropy. Experiments on UrbanBIS and STPLS3D datasets show the method outperforms state‑of‑the‑art approaches in both building instance segmentation and fine‑grained classification.
By Weiyuan Zhang, Qi Zhang, Hui Huang
arXiv:2512. 09062v2 Announce Type: replace-cross Abstract: Accurate 3D scene interpretation in active construction sites is essential for progress monitoring, safety assessment, and digital twin development.
By Seongyong Kim, Yong Kwon Cho
arXiv:2611.06180v1 Announce Type: new
Abstract: We present the Rohbau3D-Semantics dataset, which adds dense semantic and instance-level labels to laser scans of the previously released Rohbau3D domai...
By Lukas Rauch, Thomas Braml
The paper introduces a measurable semantic 3D Gaussian Splatting (3DGS) framework that uses region and depth supervision to improve building inspection from multi‑view imagery. Mask‑based region supervision focuses optimization on target areas, while point‑wise depth supervision aligns Gaussian centers with physical surfaces derived from multi‑view stereo point clouds. The resulting semantic Gaussian field enables component‑level inspection and is deployed in the AEC‑SplatTwin platform, achieving significant reductions in depth error and high semantic segmentation accuracy on UAV‑inspected and smartphone‑captured datasets.
By Yi Zhang, Tian Tan, Ray Kai Leung Su
arXiv:2608.29992v1 Announce Type: new
Abstract: This paper presents an end-to-end, agent-driven pipeline for the LoD3 reconstruction of facade openings in 3D city models, producing directly usable Ci...
By Elmehdi Kanna, Lukas Arzoumanidis, Huynh Duc An Son Nguyen, Youness Dehbi
The paper presents a two‑stage approach to street‑panorama semantic segmentation using Vision Transformer ensembles. In the first stage, nine pretrained models are compared under equal compute budgets, and the best two are trained with three random seeds, achieving 60.95% mIoU on validation and 57.08% on the hidden test leaderboard. The second stage explores augmentations, larger inputs, and additional architectures, culminating in an ensemble of four models that scores 64.53% mIoU on validation and 61.54% mIoU (71.93% F1) on the hidden test leaderboard, while the study documents all runs, costs, and releases the code and models.
By Yunus Serhat B{\i}\c{c}ak\c{c}{\i}
This paper presents an end-to-end, agent-driven pipeline for the LoD3 reconstruction of facade openings in 3D city models, producing directly usable CityGML-conform outputs. In contrast to existing ap...
arXiv:2610.08790v1 Announce Type: new
Abstract: Single-image scene generation aims to produce a complete 3D scene mesh from a single image, including surfaces the camera did not observe. While pretra...
By Jiraphon Yenphraphai, Fang Li, Tianshuo Xu, Depu Meng, Quentin Herau, Yihan Hu, Raymond A. Yeh, Wei Zhan
PhiSat‑2 offers 4.75 m multispectral imagery that can be used for monocular building‑height estimation. The authors created the PhiSat‑2–Height Dataset (PHDataset), comprising 9,475 co‑registered patch pairs from 26 cities, and developed the Two‑Stream Ordinal Network (TSONet) that uses multiscale decoupled height representation and footprint‑conditioned height reconstruction. In city‑disjoint tests, TSONet improves building RMSE and MAE by 3.64 % and 4.49 % over the best existing method, and PhiSat‑2 outperforms Sentinel‑2 and Landsat 8, demonstrating its value for urban height mapping.
By Yanjiao Song, Bowen Cai, Timo Balz, Zhenfeng Shao, Neema Simon Sumari, James Magidi, Walter Musakwa
arXiv:2606.18623v2 Announce Type: replace
Abstract: Gaussian segmentation is usually posed as transferring object knowledge from 2D foundation models into a 3D representation. This leaves a fundament...
By Mohamed Rayan Barhdadi, Hasan Yazar, Erchin Serpedin, Mehmet Tuncel, Hasan Kurban
The paper presents a semi‑automated pipeline that transforms a single 360‑degree video of a classroom into editable, simulation‑ready 3D geometry for CFD analysis. Using NeRF for dense point clouds, SAM‑based 2D instance masks lifted to 3D, and octree‑based instance separation, the workflow produces object‑level assets that can be reconfigured in a browser editor. The resulting geometry is validated with OpenFOAM simulations and benchmarked against IEA Annex 20, demonstrating that per‑room geometry acquisition is essential for accurate airflow predictions.
By Dhruv Gamdha, James Afful, Shambhavi Joshi, Ulrike Passe, Adarsh Krishnamurthy, Baskar Ganapathysubramanian
arXiv:2610.32728v1 Announce Type: new
Abstract: Generating editable 3D urban scenes from a single image requires detailed building assets with a coherent spatial arrangement. Occlusion and perspectiv...
By Haoran Gong, Jie Feng, Chenxu Wang