A family-aware Transformer with supervised contrastive learning and a diffusion-generated synthetic dataset achieves state-of-the-art 3D animal pose and shape estimation.
Smpler-x: Scaling up expressive human pose and shape estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
AniMer: Animal Pose and Shape Estimation Using Family Aware Transformer
A family-aware Transformer with supervised contrastive learning and a diffusion-generated synthetic dataset achieves state-of-the-art 3D animal pose and shape estimation.