Abstract | ||
---|---|---|
Mesh denoising is a critical technology in geometry processing, which aims to recover high-fidelity 3D mesh models of objects from noise-corrupted versions. In this work, we propose a deep learning based face normal filtering scheme for mesh denoising, called textit{NormalNet}. Different from natural images, for mesh, it is difficult to collect enough examples to build a robust end-to-end training scheme for deep networks. To remedy this problem, we propose an iterative framework to generate enough face-normal pairs, based on which a convolutional neural networks (CNNs) based scheme is designed for guidance normal learning. Moreover, to facilitate the 3D convolution operation in CNNs, for each face in mesh, we propose a voxelization strategy to transform irregular local mesh structure into regular 4D-array form. Finally, guided normal filtering is performed to obtain filtered face normals, according to which denoised positions of vertices are derived. Compared to the state-of-the-art works, the proposed scheme can generate accurate guidance normals and remove noise effectively while preserving original features and avoiding pseudo-features. |
Year | Venue | DocType |
---|---|---|
2019 | arXiv: Graphics | Journal |
Volume | Citations | PageRank |
abs/1903.04015 | 0 | 0.34 |
References | Authors | |
25 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenbo Zhao | 1 | 297 | 25.12 |
Xianming Liu | 2 | 461 | 47.55 |
Yongsen Zhao | 3 | 0 | 0.34 |
Xiaopeng Fan | 4 | 597 | 69.90 |
Debin Zhao | 5 | 3010 | 206.12 |