Trans-Unet maps 40,401-point brain-surface clouds to a 224×224 z-image and uses a CNN+attention U-Net to predict the state-3 folded surface, reporting CD=0.012 versus 45.2/36.7 for PointNet/PointNet++.
Facial uv map completion for pose- invariant face recognition: a novel adversarial approach based on coupled attention residual unets
1 Pith paper cite this work, alongside 16 external citations. Polarity classification is still indexing.
1
Pith paper citing it
16
external citations · OpenAlex
fields
cs.CV 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Toward High-Fidelity 3D Point-Cloud Learning for Brain Folding Morphology Prediction Using Trans-Unet
Trans-Unet maps 40,401-point brain-surface clouds to a 224×224 z-image and uses a CNN+attention U-Net to predict the state-3 folded surface, reporting CD=0.012 versus 45.2/36.7 for PointNet/PointNet++.