A VLM selects deformation handles and target positions, and multi-view voting produces a text-guided mesh deformation with low distortion.
Efficient learning of mesh-based physical simulation with bi-stride multi-scale graph neural network,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Handle-based Mesh Deformation Guided By Vision Language Model
A VLM selects deformation handles and target positions, and multi-view voting produces a text-guided mesh deformation with low distortion.