List your company
ResearchFormerly WizWand

Neural Super-Resolution for Mesh-Based Simulations on Dataset 3

0.0243RMSEFully supervised
0.0222560.0360530.049850.063647May 10, 2026
Updated 5mo ago

Evaluation results

MethodLinks
Fully supervisedNh (number of HR data)=200, N (number of low-resolution data)=200, Inductive biases=without inductive biases, Supervision type=full supervision, Base architecture=MGN2026.050.0243
Fully supervisedNh, N=200, 200, MPNN Architecture=MGN2026.050.0243
SuperMeshNetNh (number of HR data)=20, N (number of low-resolution data)=200, Inductive biases=with inductive biases, Supervision type=partial supervision, Base architecture=MGN2026.050.0245
SuperMeshNetNh, N=20, 200, MPNN Architecture=MGN2026.050.0245
SuperMeshNetNh, N=20, 200, MPNN Architecture=GIN2026.050.0258
SuperMeshNet-ONh, N=20, 200, MPNN Architecture=MGN2026.050.0281
SuperMeshNetNh, N=20, 200, MPNN Architecture=GTR2026.050.0294
SuperMeshNetNh, N=20, 200, MPNN Architecture=GCN2026.050.0297
SuperMeshNetNh, N=20, 200, MPNN Architecture=SAGE2026.050.0297
SuperMeshNetNh, N=20, 200, MPNN Architecture=GAT2026.050.031
SuperMeshNet-ONh, N=20, 200, MPNN Architecture=GIN2026.050.0316
Fully supervisedNh, N=200, 200, MPNN Architecture=GIN2026.050.0317
Fully supervisedNh, N=200, 200, MPNN Architecture=GTR2026.050.0329
Fully supervisedNh, N=200, 200, MPNN Architecture=SAGE2026.050.034
SuperMeshNet-ONh, N=20, 200, MPNN Architecture=GTR2026.050.0363
SuperMeshNet-ONh, N=20, 200, MPNN Architecture=SAGE2026.050.0366
Fully supervisedNh, N=200, 200, MPNN Architecture=GCN2026.050.037
Fully supervisedNh, N=200, 200, MPNN Architecture=GAT2026.050.0374
SuperMeshNet-ONh, N=20, 200, MPNN Architecture=GAT2026.050.0375
SuperMeshNet-ONh, N=20, 200, MPNN Architecture=GCN2026.050.038
Fully supervisedNh, N=20, 20, MPNN Architecture=GTR2026.050.0513
Fully supervisedNh, N=20, 20, MPNN Architecture=MGN2026.050.0523
Fully supervisedNh, N=20, 20, MPNN Architecture=GIN2026.050.0569
Fully supervisedNh, N=20, 20, MPNN Architecture=GCN2026.050.0587
Fully supervisedNh, N=20, 20, MPNN Architecture=SAGE2026.050.0611
Fully supervisedNh, N=20, 20, MPNN Architecture=GAT2026.050.0616
MAgNetNh (number of HR data)=0, N (number of low-resolution data)=200, Supervision type=no HR supervision (zero-shot)2026.050.0754