PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds

Liu, Yujia; D’Aronco, Stefano; Schindler, Konrad; Wegner, Jan Dirk

doi:10.48550/arxiv.2103.02766

Cited by 4 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, we conduct visual comparisons with several experimental methods, including three traditional approaches: 2.5D Dual Contouring (Zhou and Neumann, 2010), City3D (Huang et al, 2022), and KSR (Bauchet and Lafarge, 2020). Additionally, we compare against two recent deep learning methods, PC2WF (Liu et al, 2021) and NerVE (Zhu et al, 2023), as illustrated in Fig. 7.…”

Section: Visual and Comparative Experimentsmentioning

confidence: 99%

A Method for Roof Wireframe Reconstruction Based on Self-Supervised Pretraining

Yang,

Huang,

Wang

2024

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. In this paper, we present a two-stage method for roof wireframe reconstruction employing a self-supervised pretraining technique. The initial stage utilizes a multi-scale mask autoencoder to generate point-wise features. The subsequent stage involves three steps for edge parameter regression. Firstly, the initial edge directions are generated under the guidance of edge point identification. The next step employs edge parameter regression and matching modules to extract the parameters (namely, direction vector and length) of edge representation from the obtained edge features. Finally, a specifically designed edge non-maximum suppression and an edge similarity loss function are employed to optimize the representation of the final wireframe models and eliminate redundant edges. Experimental results indicate that the pre-trained self-supervised model, enriched by the roof wireframe reconstruction task, demonstrates superior performance on both the publicly available Building3D dataset and its post-processed iterations, specifically the Dense dataset, outperforming even traditional methods.

show abstract

Section: Visual and Comparative Experimentsmentioning

confidence: 99%

A Method for Roof Wireframe Reconstruction Based on Self-Supervised Pretraining

Yang,

Huang,

Wang

2024

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The PointNet architecture was the first applied directly to 3D point clouds, introducing a new era in 3D point-cloud analysis. Liu et al [30] introduced an end-to-end trainable deep network architecture which automatically generates a 3D graph representation of a given 3D point cloud of man-made polyhedral objects such as furniture, mechanical parts, or building interiors, etc.…”

Section: Related Workmentioning

confidence: 99%

Point-Cloud Segmentation for 3D Edge Detection and Vectorization

Betsas¹,

Georgopoulos²

2022

Heritage

View full text Add to dashboard Cite

The creation of 2D–3D architectural vector drawings constitutes a manual, labor-intensive process. The scientific community has not provided an automated approach for the production of 2D–3D architectural drawings of cultural-heritage objects yet, regardless of the undoubtable need of many scientific fields. This paper presents an automated method which addresses the problem of detecting 3D edges in point clouds by leveraging a set of RGB images and their 2D edge maps. More concretely, once the 2D edge maps have been produced exploiting manual, semi-automated or automated methods, the RGB images are enriched with an extra channel containing the edge semantic information corresponding to each RGB image. The four-channel images are fed into a Structure from Motion–Multi View Stereo (SfM-MVS) software and a semantically enriched dense point cloud is produced. Then, using the semantically enriched dense point cloud, the points belonging to a 3D edge are isolated from all the others based on their label value. The detected 3D edge points are decomposed into set of points belonging to each edge and fed into the 3D vectorization procedure. Finally, the 3D vectors are saved into a “.dxf” file. The previously described steps constitute the 3DPlan software, which is available on GitHub. The efficiency of the proposed software was evaluated on real-world data of cultural-heritage assets.

show abstract

“…Such methods are not directly applicable to our setup. The most direct competitors are PIE-Net [20] and PC2WF [14]. PIE-Net utilizes a standard PointNet++ architecture to obtain the sharp edge segmentation and detect corners.…”

Section: Related Workmentioning

confidence: 99%

3D Parametric Wireframe Extraction Based on Distance Fields

Matveev,

Artemov,

Zorin

et al. 2021

Preprint

View full text Add to dashboard Cite

Fig. 1. Parametric wireframe extraction pipeline: (a) -dense point cloud with estimated distance field, (b) -sharp point skeleton with color-coded segmentation into individual curves (note the black clusters corresponding to the detected corner neighborhoods), (c) -optimized topological graph with final corner points (red), (d) -extracted parametric wireframe, (e) -ground-truth parametric wireframe.We present a pipeline for parametric wireframe extraction from densely sampled point clouds. Our approach processes a scalar distance field that represents proximity to the nearest sharp feature curve. In intermediate stages, it detects corners, constructs curve segmentation, and builds a topological graph fitted to the wireframe. As an output, we produce parametric spline curves that can be edited and sampled arbitrarily. We evaluate our method on 50 complex 3D shapes and compare it to the novel deep learning-based technique, demonstrating superior quality.CCS Concepts: • Computing methodologies → Parametric curve and surface models; Point-based models.

show abstract

PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds

Cited by 4 publications

References 45 publications

A Method for Roof Wireframe Reconstruction Based on Self-Supervised Pretraining

A Method for Roof Wireframe Reconstruction Based on Self-Supervised Pretraining

Point-Cloud Segmentation for 3D Edge Detection and Vectorization

3D Parametric Wireframe Extraction Based on Distance Fields

Contact Info

Product

Resources

About