A flow-matching model with Earth Mover's Distance pre-alignment upsamples point clouds in five sampling steps, with state-of-the-art Chamfer distance scores on PUGAN and PU1K.
Grad-pu: Arbitrary- scale point cloud upsampling via gradient descent with learned distance functions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Point Clouds Upsampling via Flow Matching
A flow-matching model with Earth Mover's Distance pre-alignment upsamples point clouds in five sampling steps, with state-of-the-art Chamfer distance scores on PUGAN and PU1K.