|国家预印本平台
首页|Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction

Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction

Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction

来源:Arxiv_logoArxiv
英文摘要

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.

Zezeng Li、Zhihui Qi、Weimin Wang、Ziliang Wang、Junyi Duan、Na Lei

10.1109/TCSVT.2025.3556130

计算技术、计算机技术

Zezeng Li,Zhihui Qi,Weimin Wang,Ziliang Wang,Junyi Duan,Na Lei.Point2Quad: Generating Quad Meshes from Point Clouds via Face Prediction[EB/OL].(2025-04-28)[2025-07-16].https://arxiv.org/abs/2504.19545.点此复制

评论