A two-stage method synthesizes multi-view 2D motion data from internet video keypoints and trains a camera-conditioned diffusion model to recover globally consistent 3D human motion and HOI in world space.
Trace: 5d temporal regression of avatars with dynamic cam- eras in 3d environments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion
A two-stage method synthesizes multi-view 2D motion data from internet video keypoints and trains a camera-conditioned diffusion model to recover globally consistent 3D human motion and HOI in world space.