Lightweight and accurate building models have been widely used in diverse applications such as urban planning, virtual reality, and navigation. In recent years, structure-aware building reconstruction has emerged as a crucial research area. Despite significant advancements in measurement techniques such as Light Detection and Ranging (LiDAR) and photogrammetry, the raw data often contains different types of imperfections, such as noise, outliers, and missing regions. These imperfections pose challenges for the accurate and efficient reconstruction of complex building structures. Therefore, this thesis aims to address these challenges by proposing methods for automatic Level of Detail 2 (LoD2) building reconstruction from airborne LiDAR point clouds, and semi-automatic Level of Detail 3 (LoD3) building reconstruction from Multi-View Stereo (MVS) meshes. Throughout the reconstruction process, structural details are easily distorted in the final output due to the inaccuracies and imperfections of input data. Given that regularities such as symmetry are prevalent in building models, they can be leveraged to recover lost or distorted building structures. To facilitate the recovery of symmetry, building elements are projected into facade planes to be two-dimensional (2D) polygonal shapes. Therefore, to obtain accurate and aesthetically pleasing models, this thesis also focuses on recovering the symmetry of these 2D polygonal shapes generated from buildings.

My first contribution is city-scale LoD2 building reconstruction from airborne LiDAR point clouds. While LiDAR data provides rich geometric information, reconstructing detailed building models at such a large scale remains an open problem. This thesis proposes a novel method to tackle this problem, achieving accurate city-scale LoD2 building reconstruction. Firstly, I use footprint data to segment out the point clouds of individual building instances. Then, I detect planar primitives using a region-growing algorithm and infer wall primitives by applying a vertical assumption on the missing regions. Then an abundant set of candidate faces is generated by intersecting the planes derived from roof and wall primitives. Finally, I can obtain a compact building model by selecting the optimal subset of candidate faces through solving an integer programming problem. Geometry constraints are enforced to ensure that the final model is manifold and watertight.

My second contribution is a semi-automatic method for reconstructing LoD3 building models from MVS meshes. While MVS techniques can generate dense and detailed triangular surfaces, creating compact and accurate LoD3 models from them remains challenging due to the limited data resolution. The proposed method is designed to strike a balance between human interactions and automation, aiming to maximize efficiency while minimizing user efforts. The process begins with a coarse segmentation using variational shape approximation. Then, simple and intuitive operations are introduced to refine the segmentation results by solving a multi-label optimization problem. At this stage, the user’s involvement is minimal and limited to providing high-level guidance, ensuring that the system remains user-friendly. Importantly, these interactions are kept to a minimum, allowing users to make adjustments without requiring precise input, making the process more efficient than manual reconstruction. Finally, the face normals and vertices of the mesh are updated based on the refined segmentation, and the layout of the model is regularized to produce an accurate LoD3 building model. This semi-automatic approach combines the strengths of both user input and automated computation, offering a practical solution for detailed building reconstruction that is both effective and user-friendly.

My third contribution is a novel algorithm to automatically symmetrize 2D polygonal shapes, which is essential to regularize the shapes and enhance the visual aesthetics of building models. The method follows a hypothesis-and-selection pipeline. Taking a 2D polygonal shape generated from a building model as input, I first generate a set of potential symmetric edge pairs. Then the initial set is pruned by two simple geometric tests. Finally, a perfectly symmetric shape is obtained by solving a mixed integer quadratic programming problem. Two hard constraints are imposed to ensure that the final shape to be symmetric. The method is also designed to handle partial symmetry in cases where perfect symmetry is not achievable.

In summary, I first automatically reconstruct LoD2 building models from airborne LiDAR point clouds. Then, I reconstruct LoD3 building models from MVS meshes by incorporating user guidance, which depicts a more detailed representation of building models. To obtain more accurate and visually pleasing building models, I propose to symmetrize the 2D polygonal shapes generated from facade elements of reconstructed models.@en

Symmetry widely exists in nature and man-made shapes, but it is unavoidably distorted during the process of growth, design, digitalization, and reconstruction steps. To enhance symmetry, traditional methods follow the detect-then-symmetrize paradigm, which is sensitive to noise in the detection phase, resulting in ambiguities for the subsequent symmetrization step. In this work, we propose a novel optimization-based framework that jointly detects and optimizes symmetry for 2D shapes represented as polygons. Our method can detect and optimize symmetry using a single objective function. Specifically, we formulate symmetry detection and optimization as a mixed-integer program. Our method first generates a set of candidate symmetric edge pairs, which are then encoded as binary variables in our optimization. The geometry of the shape is expressed as continuous variables, which are then optimized together with the binary variables. The symmetry of the shape is enforced by the designed hard constraints. After the optimization, both the optimal symmetric edge correspondences and the geometry are obtained. Our method simultaneously detects all the symmetric primitive pairs and enhances the symmetry of a model while minimally altering its geometry. We have tested our method on a variety of shapes from designs and vectorizations, and the results have demonstrated its effectiveness.

@en

We present a fully automatic approach for reconstructing compact 3D building models from large-scale airborne point clouds. A major challenge of urban reconstruction from airborne LiDAR point clouds lies in that the vertical walls are typically missing. Based on the observation that urban buildings typically consist of planar roofs connected with vertical walls to the ground, we propose an approach to infer the vertical walls directly from the data. With the planar segments of both roofs and walls, we hypothesize the faces of the building surface, and the final model is obtained by using an extended hypothesis-and-selection-based polygonal surface reconstruction framework. Specifically, we introduce a new energy term to encourage roof preferences and two additional hard constraints into the optimization step to ensure correct topology and enhance detail recovery. Experiments on various large-scale airborne LiDAR point clouds have demonstrated that the method is superior to the state-of-the-art methods in terms of reconstruction accuracy and robustness. In addition, we have generated a new dataset with our method consisting of the point clouds and 3D models of 20k real-world buildings. We believe this dataset can stimulate research in urban reconstruction from airborne LiDAR point clouds and the use of 3D city models in urban applications@en