GenCape uses an iterative structure-aware variational autoencoder and compositional graph transfer to infer keypoint relationships from image support inputs, achieving gains over graph baselines on MP-100 under 1- and 5-shot settings.
arXiv preprint arXiv:2411.06869 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation
GenCape uses an iterative structure-aware variational autoencoder and compositional graph transfer to infer keypoint relationships from image support inputs, achieving gains over graph baselines on MP-100 under 1- and 5-shot settings.