A self-supervised multimodal approach for non-rigid 3D shape matching that achieves state-of-the-art results on benchmarks and previously unseen cross-dataset generalization.
Scape: shape completion and animation of people
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2023 2verdicts
UNVERDICTED 2representative citing papers
Introduces self-adaptive functional map solver and vertex-wise contrastive loss for improved unsupervised non-rigid 3D shape matching on challenging datasets.
citing papers explorer
-
Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching
A self-supervised multimodal approach for non-rigid 3D shape matching that achieves state-of-the-art results on benchmarks and previously unseen cross-dataset generalization.
-
Revisiting Map Relations for Unsupervised Non-Rigid Shape Matching
Introduces self-adaptive functional map solver and vertex-wise contrastive loss for improved unsupervised non-rigid 3D shape matching on challenging datasets.