Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Zezeng, Qi, Zhihui, Wang, Weimin, Wang, Ziliang, Duan, Junyi, Lei, Na
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2504.19545
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915262702288896
author Li, Zezeng
Qi, Zhihui
Wang, Weimin
Wang, Ziliang
Duan, Junyi
Lei, Na
author_facet Li, Zezeng
Qi, Zhihui
Wang, Weimin
Wang, Ziliang
Duan, Junyi
Lei, Na
contents Quad meshes are essential in geometric modeling and computational mechanics. Although learning-based methods for triangle mesh demonstrate considerable advancements, quad mesh generation remains less explored due to the challenge of ensuring coplanarity, convexity, and quad-only meshes. In this paper, we present Point2Quad, the first learning-based method for quad-only mesh generation from point clouds. The key idea is learning to identify quad mesh with fused pointwise and facewise features. Specifically, Point2Quad begins with a k-NN-based candidate generation considering the coplanarity and squareness. Then, two encoders are followed to extract geometric and topological features that address the challenge of quad-related constraints, especially by combining in-depth quadrilaterals-specific characteristics. Subsequently, the extracted features are fused to train the classifier with a designed compound loss. The final results are derived after the refinement by a quad-specific post-processing. Extensive experiments on both clear and noise data demonstrate the effectiveness and superiority of Point2Quad, compared to baseline methods under comprehensive metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19545
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction
Li, Zezeng
Qi, Zhihui
Wang, Weimin
Wang, Ziliang
Duan, Junyi
Lei, Na
Computer Vision and Pattern Recognition
Artificial Intelligence
Quad meshes are essential in geometric modeling and computational mechanics. Although learning-based methods for triangle mesh demonstrate considerable advancements, quad mesh generation remains less explored due to the challenge of ensuring coplanarity, convexity, and quad-only meshes. In this paper, we present Point2Quad, the first learning-based method for quad-only mesh generation from point clouds. The key idea is learning to identify quad mesh with fused pointwise and facewise features. Specifically, Point2Quad begins with a k-NN-based candidate generation considering the coplanarity and squareness. Then, two encoders are followed to extract geometric and topological features that address the challenge of quad-related constraints, especially by combining in-depth quadrilaterals-specific characteristics. Subsequently, the extracted features are fused to train the classifier with a designed compound loss. The final results are derived after the refinement by a quad-specific post-processing. Extensive experiments on both clear and noise data demonstrate the effectiveness and superiority of Point2Quad, compared to baseline methods under comprehensive metrics.
title Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.19545