EnergyMoGen combines a latent-aware energy-based composition and a semantic-aware cross-attention energy model, fused by Synergistic Energy Fusion, to generate motions satisfying multiple textual concepts.
Black, and G¨ul Varol
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
EnergyMoGen: Compositional Human Motion Generation with Energy-Based Diffusion Model in Latent Space
EnergyMoGen combines a latent-aware energy-based composition and a semantic-aware cross-attention energy model, fused by Synergistic Energy Fusion, to generate motions satisfying multiple textual concepts.