UV-Net
A graph neural network designed specifically for B-Rep solid models. Each face of the model is parameterized as a feature grid in a UV coordinate system, and global information is aggregated through a face adjacency graph, enabling face-level semantic segmentation of boundary representation geometry.
Timeline (last 90 days)
The study introduces two representative B-Rep segmentation models, UV-Net and AAGNet, and trains them on a newly constructed manually annotated benchmark dataset.
UV-Net is a graph neural network designed specifically for B-Rep, which parameterizes each face as a feature map in UV coordinate space and aggregates global information through a face adjacency graph to achieve face-level semantic segmentation.
Learning-based methods can achieve very strong performance when annotated data is sufficient, but their robustness degrades significantly when facing domain shift.
All Facts (3)
The study introduces two representative B-Rep segmentation models, UV-Net and AAGNet, and trains them on a newly constructed manually annotated benchmark dataset.
50%UnverifiedUV-Net is a graph neural network designed specifically for B-Rep, which parameterizes each face as a feature map in UV coordinate space and aggregates global information through a face adjacency graph to achieve face-level semantic segmentation.
50%UnverifiedLearning-based methods can achieve very strong performance when annotated data is sufficient, but their robustness degrades significantly when facing domain shift.
50%