Structure-aware Building Mesh Polygonization

Bouzas, Vasileios; Ledoux, Hugo; Nan, Liangliang

doi:10.1016/j.isprsjprs.2020.07.010

Cited by 33 publications

(28 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is easy to fail during the generation of the polyhedron model in this case, so these regions that are supposed to be in the same plane should be merged. SABMP [23] traverses all plane regions and merges the approximately parallel plane regions with small spatial distance into a new plane region. And the entire traversal process is repeated until no new region is created.…”

Section: The Merging Of Coplanar Plane Regionsmentioning

confidence: 99%

“…These methods mainly maintain the edge features and surface connection relations but do not make good use of the abundant prior topological information of artificial features. Bouzas et al [23] proposed a Structure-Aware Building Mesh Polygonization (SABMP) strategy to generate a manifold watertight polyhedral model after segmentation, construction of structure graph, and candidate face generation and optimization. This approach is not ideal in terms of ease of use and model quality.…”

Section: Introductionmentioning

confidence: 99%

“…Each of these algorithms has its advantages and disadvantages, and the segmentation effect depends on fine-tuning parameters, such as the distance to the plane and the area of the plane region. The work of Bouzas et al [23] takes the distance between triangular facet and plane to grow the region, and it deletes the plane region whose area proportion is less than the threshold value. The setting of these parameters requires a lot of experience, and the threshold setting varies from building to building.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Urban Building Mesh Polygonization Based on 1-Ring Patch and Topology Optimization

Xie

2021

Remote Sensing

View full text Add to dashboard Cite

With the development of UAV and oblique photogrammetry technology, the multi-view stereo image has become an important data source for 3D urban reconstruction, and the surface meshes generated by it have become a common way to represent the building surface model due to their high geometric similarity and high shape representation ability. However, due to the problem of data quality and lack of building structure information in multi-view stereo image data sources, it is a huge challenge to generate simplified polygonal models from building surface meshes with high data redundancy and fuzzy structural boundaries, along with high time consumption, low accuracy, and poor robustness. In this paper, an improved mesh representation strategy based on 1-ring patches is proposed, and the topology validity is improved on this basis. Experimental results show that our method can reconstruct the concise, manifold, and watertight surface models of different buildings, and it can improve the processing efficiency, parameter adaptability, and model quality.

show abstract

Section: The Merging Of Coplanar Plane Regionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Urban Building Mesh Polygonization Based on 1-Ring Patch and Topology Optimization

Xie

2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Furthermore, Verdie et al (2015) propose an approach for reconstructing urban scenes with various LoD configurations from dense meshes. Bouzas et al (2020b) incorporates structure awareness with the recovery and preservation of the initial mesh primitives and their adjacencies. Li and Nan (2021) further exploits the preservation of piecewise planar structures and sharp features.…”

Section: Geometric Simplificationmentioning

confidence: 99%

“…Figure 1 illustrates a building described as a smooth surface and piecewise-planar ones, where an arbitrary-sided polygonal surface exhibits the highest compactness. Although some works claim the possibility of reconstructing compact surface models from point clouds (Boulch et al, 2014;Mura et al, 2016;Li et al, 2016b;Nan and Wonka, 2017) or dense triangle meshes (Bouzas et al, 2020a), or simplifying existing models (Li and Nan, 2021), they suffer from serious scalability issues. In this paper, we aim at robust reconstruction of compact building surfaces directly from point clouds.…”

Section: Introductionmentioning

confidence: 99%

Reconstructing Compact Building Models from Point Clouds Using Deep Implicit Fields

Zhaiyu¹,

Khademi²,

Ledoux³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Three-dimensional (3D) building models play an increasingly pivotal role in many real-world applications, while obtaining a compact representation of buildings remains an open problem. In this paper, we present a novel framework for reconstructing compact, watertight, polygonal building models from point clouds. Our framework comprises three components: (a) a cell complex is generated via adaptive space partitioning that provides a polyhedral embedding as the candidate set; (b) an implicit field is learned by a deep neural network that facilitates building occupancy estimation; (c) a Markov random field is formulated to extract the outer surface of a building via combinatorial optimization. We evaluate and compare our method with state-of-the-art methods in shape reconstruction, surface approximation, and geometry simplification. Experiments on both synthetic and real-world point clouds have demonstrated that, with our neural-guided strategy, high-quality building models can be obtained with significant advantages in fidelity, compactness, and computational efficiency. Our method shows robustness to noise and insufficient measurements, and it can directly generalize from synthetic scans to real-world measurements.

show abstract

Efficient High-Quality Vectorized Modeling of Large-Scale Scenes

Xiang,

Jiang,

et al. 2024

Int J Comput Vis

View full text Add to dashboard Cite

Structure-aware Building Mesh Polygonization

Cited by 33 publications

References 16 publications

Urban Building Mesh Polygonization Based on 1-Ring Patch and Topology Optimization

Urban Building Mesh Polygonization Based on 1-Ring Patch and Topology Optimization

Reconstructing Compact Building Models from Point Clouds Using Deep Implicit Fields

Efficient High-Quality Vectorized Modeling of Large-Scale Scenes

Contact Info

Product

Resources

About