SemLite-GS: Semantic-Selective Parallel Gaussian Splatting for Lightweight Building Reconstruction from UAV Oblique Imagery
Organizations: School of Geodesy and Geomatics, Wuhan University, Wuhan, 430079, China · Space Engineering University, Beijing, 102299, China
Abstract
Lightweight 3D building models support urban spatial analysis, but their production often requires dense scene reconstruction, building extraction, and mesh simplification. Although 3D Gaussian Splatting (3DGS) is more efficient than conventional multi-view stereo, existing large-scale methods lack semantic selection and parallel instance-level training. We present SemLite-GS, a building-centric framework that reconstructs lightweight building meshes from large-scale UAV oblique imagery. First, an orthographic reference map establishes globally consistent building identities, which are propagated to oblique views to form camera-instance pairs and regions of interest. Second, semantic-selective parallel PGSR training jointly processes multiple pairs within relevant image regions while updating only target Gaussians; contextual Gaussians remain fixed to preserve visibility. Third, architectural planes extracted from rendered depth, opacity, and normal maps guide signed distance field optimization, producing meshes with adaptive polygon allocation and well-defined structural boundaries. Experiments on multiple large-scale UAV datasets demonstrate that our SemLite-GS substantially reduces building reconstruction time compared with representative full-scene 3DGS methods. With comparable polygon budgets, SemLite-GS achieves superior preservation of dominant planar structures and sharp architectural transitions compared with conventional dense reconstruction followed by mesh decimation. The source code is available at https://github.com/IRIS-LAB-whu/SemLite-GS.
Figures & tables
| Dataset | Scene | # Images | Resolution | Target instances | LiDAR |
| GauScene | CUHK_LOWER | 670 | 18 | Yes | |
| CUHK_UPPER | 715 | 22 | Yes | ||
| SZIT | 1,215 | 26 | Yes | ||
| Skylume | building | 3,646 | 24 | Yes | |
| tec_school | 2,394 | 11 | Yes | ||
| Tianjin_Xiqing | Tianjin_Xiqing | 305 | 34 | No |
| Dataset | Scene | Valid instances | Pipeline | CD (m) | Avg. vertices | Avg. faces |
| GauScene | CUHK_LOWER | 18 | CityGS-X + QEM | 2.305 | 282 | 1000 |
| CityGaussianV2 + QEM | 1.559 | 384 | 1000 | |||
| SemLite-GS (TSDF) + QEM | 1.528 | 407 | 1000 | |||
| PG-SAG + QEM | 1.373 | 563 | 1000 | |||
| PG-SAG (mask) + QEM | 1.031 | 578 | 1000 | |||
| Metashape + QEM | 1.154 | 582 | 1000 |
| CD (m) | ||||||||
| Dataset | Scene | Valid instances | SemLite-GS | PG-SAG | PG-SAG (mask) | CityGaussianV2 | CityGS-X | Metashape |
| GauScene | CUHK_LOWER | 18 | 0.833 | 1.306 | 0.952 | 1.214 | 1.455 | 1.140 |
| CUHK_UPPER | 22 | 0.807 | 0.972 | 0.902 | 1.033 | 1.904 | 1.165 | |
| SZIT | 26 | 0.972 | 1.344 | 1.022 | 1.241 | 1.633 | 1.574 | |
| Skylume | building | 24 | 0.481 | 1.043 | 0.693 | 0.705 | 1.148 | 0.611 |
| tec_school | 11 | 0.445 | 0.657 | 0.484 | 0.601 | 0.984 | 0.681 | |
| Pipeline | Preprocessing (h) | Training (h) | Mesh reconstruction (h) | Total time (h) |
| CityGS-X + QEM | 0.40 | 12.19 | 1.49 | 14.08 |
| CityGaussianV2 + QEM | 0.43 | 72.38 | 1.06 | 73.87 |
| PG-SAG + QEM | 1.07 | 9.29 | 0.64 | 11.00 |
| Metashape + QEM | – | – | 3.57 | 3.57 |
| SemLite-GS | 0.64 | 2.31 | 0.53 | 3.48 |
| Dataset | Scene | Valid instances | Method | CD (m) | Avg. vertices | Avg. faces |
| GauScene | CUHK_LOWER | 18 | PolyFit 10/18 | 3.380 | 204 | 208 |
| KSR | 5.729 | 441 | 792 | |||
| Compod | 2.670 | 414 | 860 | |||
| SemLite-GS | 1.026 | 546 | 998 | |||
| CUHK_UPPER | 22 | PolyFit 5/22 | 3.906 | 115 | 101 | |
| KSR | 4.215 | 414 | 772 |
| Scene | Images | Independent SAM3 (s) | SemLite-GS (s) |
| building | 3,646 | 1,031.3 | 298.0 |
| tec_school | 2,394 | 677.5 | 148.1 |
| CD (m) | |||
| Scene | TSDF mesh | Lightweight mesh | |
| building (24) | Without | 0.556 | 0.727 |
| With | 0.481 | 0.702 | |
| tec_school (11) | Without | 0.460 | 0.652 |
| With | 0.445 | 0.616 | |
| Overall (35) | Without | 0.526 | 0.703 |
| Scene | Pairs ( ) | Time (s) | Peak memory (GiB) |
| building | 1 | 6693.5 | 8.95 |
| 2 | 4867.8 | 10.39 | |
| 4 | 3766.2 | 15.58 | |
| 8 | 2998.0 | 22.86 | |
| tec_school | 1 | 2214.2 | 5.25 |
| 2 | 1593.2 | 6.22 |
| Scene | Configuration | Time (s) | GPU (GiB) |
| building (24) | (CPU) | 2555.2 | 19.41 |
| (CPU) | 2404.1 | 22.91 | |
| tec_school (8) | (GPU) | 690.7 | 20.05 |
3D Reconstruction
3D reconstruction recovers a scene’s shape, appearance, and camera motion from images, video, depth, or other sensor measurements.
See all 1,017 papers