Thanks to visit codestin.com
Credit goes to github.com

Skip to content

GINOT is a deep learning model that combines transformers with neural operators for accurate forward predictions on arbitrary 2D and 3D geometries. It processes surface point clouds using attention-based encoding with sampling and grouping, ensuring robustness to point density, order invariance, and padding resilience.

Notifications You must be signed in to change notification settings

QibangLiu/GINOT

Repository files navigation

Geometry-Informed Neural Operator Transformer

Overview of model architectures

Figure 1: Overview of GINOT architecture. The boundary points cloud is initially processed through sampling and grouping layers to extract local geometric features. These local features are then fused with global geometric information via a cross-attention layer. This is followed by a series of self-attention layers and a final linear layer, producing the KEY and VALUE matrices for the cross-attention layer in the solution decoder. In the solution decoder, an MLP encodes the query points into the QUERY matrix for the cross-attention layer, which integrates the geometry information from the encoder. The output of the cross-attention layer is subsequently decoded into solution fields at the query points using another MLP.

Examples

Animation of pub median case

Figure 2: Visualization of Mises stress and displacement solutions for the median testing case of the micro-periodic unit cell. The first column shows the input surface points cloud, the second column presents the true stress on the actual deformed shape, the third column depicts the predicted stress on the predicted deformed shape, and the fourth column highlights the absolute error of stress on the actual deformed shape.

Figure 3: Mises stress solutions for the median (top row) and worst (bottom row) testing samples of the JEB dataset. Each row shows (from left to right): the input surface point cloud, the ground truth from finite element analysis, the GINOT prediction, and the absolute error between prediction and ground truth.

Dataset

The dataset used for training and evaluation is publicly available on Zenodo, except for the micro-periodic unit cell dataset, which is avilable on https://doi.org/10.5281/zenodo.15121966. Please download these datasets and unzip into ./data

Reference

About

GINOT is a deep learning model that combines transformers with neural operators for accurate forward predictions on arbitrary 2D and 3D geometries. It processes surface point clouds using attention-based encoding with sampling and grouping, ensuring robustness to point density, order invariance, and padding resilience.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published