A feedforward network trained only on 2D foundation-model features predicts rotation-robust, general-purpose 3D mesh features that work zero-shot for segmentation, correspondence, and deformation.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MeshFM: 2D Features Are All You Need for 3D Shape Understanding
A feedforward network trained only on 2D foundation-model features predicts rotation-robust, general-purpose 3D mesh features that work zero-shot for segmentation, correspondence, and deformation.