UVTran predicts auxiliary projection surfaces via cross-attention transformers and voxelized classification to achieve more accurate parameterization for N-sided hole filling in trimmed B-spline surfaces.
PointNext:RevisitingPointNet++withimproved training and scaling strategies
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
UVTran: Accurate Hole-Filling Parameterization with Transformers
UVTran predicts auxiliary projection surfaces via cross-attention transformers and voxelized classification to achieve more accurate parameterization for N-sided hole filling in trimmed B-spline surfaces.