A transformer-based two-stage network predicts static hair drapes and dynamic hair motion for arbitrary hairstyles and body poses in real time, trained with physics-inspired losses rather than pre-simulated data.
Artur Grigorev, Michael J Black, and Otmar Hilliges
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HairFormer: Transformer-Based Dynamic Neural Hair Simulation
A transformer-based two-stage network predicts static hair drapes and dynamic hair motion for arbitrary hairstyles and body poses in real time, trained with physics-inspired losses rather than pre-simulated data.