Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks
arXiv:2107.02909
Abstract
This paper addresses mesh restoration problems, i.e., denoising and completion, by learning self-similarity in an unsupervised manner. For this purpose, the proposed method, which we refer to as Deep Mesh Prior, uses a graph convolutional network on meshes to learn the self-similarity. The network takes a single incomplete mesh as input data and directly outputs the reconstructed mesh without being trained using large-scale datasets. Our method does not use any intermediate representations such as an implicit field because the whole process works on a mesh. We demonstrate that our unsupervised method performs equally well or even better than the state-of-the-art methods using large-scale datasets.
arXiv comment10 pages, 9 figures and 2 tables
References in corpus (7)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Fast Graph Representation Learning with PyTorch Geometric
- MeshCNN: A Network with an Edge
- PCPNET: Learning Local Shape Properties from Raw Point Clouds
- Unpaired Point Cloud Completion on Real Scans using Adversarial Training
- DNF-Net: a Deep Normal Filtering Network for Mesh Denoising