Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks
This addresses mesh restoration for computer graphics and vision applications, offering an unsupervised approach that avoids large datasets, though it appears incremental as it builds on graph convolutional networks.
The paper tackles mesh restoration problems like denoising and completion by learning self-similarity in an unsupervised manner, achieving performance equal to or better than state-of-the-art methods that use large-scale datasets.
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.