A diffusion model over per-person UNet weights generates new dynamic human avatars that render pose-dependent 3D Gaussians in real time.
Neus2: Fast learning of neural implicit surfaces for multi-view recon- struction
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
-
Hyper Diffusion Avatars: Dynamic Human Avatar Generation using Network Weight Space Diffusion
A diffusion model over per-person UNet weights generates new dynamic human avatars that render pose-dependent 3D Gaussians in real time.