Submitted anonymously.

Submission data

Full nameMesh Neural Networks Based on Dual Graph Pyramids
DescriptionDeep neural networks (DNNs) have been widely used for mesh processing in recent years. However, current DNNs can not process arbitrary meshes efficiently. On the one hand, most DNNs expect 2-manifold, watertight meshes, but many meshes, whether manually designed or automatically generated, may have gaps, non-manifold geometry, or other defects. On the other hand, the irregular structure of meshes also brings challenges to building hierarchical structures and aggregating local geometric information, which is critical to conduct DNNs. In this paper, we present DGNet, an efficient, effective and generic deep neural mesh processing network based on dual graph pyramids; it can handle arbitrary meshes. Firstly, we construct dual graph pyramids for meshes to guide feature propagation between hierarchical levels for both downsampling and upsampling. Secondly, we propose a novel convolution to aggregate local features on the proposed hierarchical graphs. By utilizing both geodesic neighbors and
Input Data TypesUses Geometry        Uses 3D
Programming language(s)python
Hardware3090
Submission creation date15 Apr, 2022
Last edited10 Mar, 2023

3D semantic label results

Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
0.6840.7120.7840.7820.6580.8350.4990.8230.6410.5970.9500.4870.2810.5750.6190.6470.7640.6200.8710.8460.688