A latent-space transformer framework poses 3D characters without skinning or fixed topologies, outperforming baselines and generalizing zero-shot to quadrupeds.
HumanRAM: Feed-forward human reconstruction and animation model using transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters
A latent-space transformer framework poses 3D characters without skinning or fixed topologies, outperforming baselines and generalizing zero-shot to quadrupeds.