Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian

no code implementations • 4 Sep 2023 • Zixiong Wang, Yunxiao Zhang, Rui Xu, Fan Zhang, PengShuai Wang, Shuangmin Chen, Shiqing Xin, Wenping Wang, Changhe Tu

Our approach enforces the Hessian of the neural implicit function to have a zero determinant for points near the surface.

A Task-driven Network for Mesh Classification and Semantic Part Segmentation

no code implementations • 8 Jun 2023 • Qiujie Dong, Xiaoran Gong, Rui Xu, Zixiong Wang, Shuangmin Chen, Shiqing Xin, Changhe Tu, Wenping Wang

With the rapid development of geometric deep learning techniques, many mesh-based convolutional operators have been proposed to bridge irregular mesh structures and popular backbone networks.

Segmentation Semantic Segmentation

Laplacian2Mesh: Laplacian-Based Mesh Understanding

1 code implementation • 1 Feb 2022 • Qiujie Dong, Zixiong Wang, Manyi Li, Junjie Gao, Shuangmin Chen, Zhenyu Shu, Shiqing Xin, Changhe Tu, Wenping Wang

Geometric deep learning has sparked a rising interest in computer graphics to perform shape understanding tasks, such as shape classification and semantic segmentation.

Semantic Segmentation Surface Reconstruction

Neural-IMLS: Self-supervised Implicit Moving Least-Squares Network for Surface Reconstruction

1 code implementation • 9 Sep 2021 • Zixiong Wang, Pengfei Wang, PengShuai Wang, Qiujie Dong, Junjie Gao, Shuangmin Chen, Shiqing Xin, Changhe Tu, Wenping Wang

We conducted extensive experiments on various benchmarks, including synthetic scans and real scans.

Surface Reconstruction