Figure 1: A large-scale urban architectural scene is automatically and efficiently reconstructed in details from a noisy and sparse LiDAR scan using our method without user interactions. Zoom-in views show the reconstructed details of 3D repetitive structures. There are totally 478, 172, 981 points within the scans and the reconstruction time is less than one hour.
AbstractModeling of urban facades from raw LiDAR point data remains active due to its challenging nature. In this paper, we propose an automatic yet robust 3D modeling approach for urban facades with raw LiDAR point clouds. The key observation is that building facades often exhibit repetitions and regularities. We hereby formulate repetition detection as an energy optimization problem with a global energy function balancing geometric errors, regularity and complexity of facade structures. As a result, repetitive structures are extracted robustly even in the presence of noise and missing data. By registering repetitive structures, missing regions are completed and thus the associated point data of structures are well consolidated. Subsequently, we detect the potential design intents (i.e., geometric constraints) within structures and perform constrained fitting to obtain the precise structure models. Furthermore, we apply structure alignment optimization to enforce position regularities and employ repetitions to infer missing structures. We demonstrate how the quality of raw LiDAR data can be improved by exploiting data redundancy, and discovering high level structural information (regularity and symmetry). We evaluate our modeling method on a variety of raw LiDAR scans to verify its robustness and effectiveness.
J. Wang et al. / Automatic Modeling of Urban Facades from Raw LiDAR Point Dataand constraints of facade structures directly over raw LiDAR point cloud data. With different scales, the urban facades usually present a high degree of symmetry and their attached structures (e.g., windows) are often regularly repeated. Based on this observation, our facade modeling method proceeds as repetitive structure detection, fitting and locating.