Unsupervised 3D human pose estimation from single views using conditional multi-view ancestral sampling on 2D diffusion priors, with improved cross-domain results on extreme poses.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
RK4 at 80 function evaluations matches Euler at 200 in sliced Wasserstein quality for flow matching sampling, with the adaptive solver concentrating steps near t=1 due to stiffening velocity fields.
citing papers explorer
-
Unsupervised 3D Human Pose Estimation via Conditional Multi-view Ancestral Sampling
Unsupervised 3D human pose estimation from single views using conditional multi-view ancestral sampling on 2D diffusion priors, with improved cross-domain results on extreme poses.
-
From Euler to Dormand-Prince: ODE Solvers for Flow Matching Generative Models
RK4 at 80 function evaluations matches Euler at 200 in sliced Wasserstein quality for flow matching sampling, with the adaptive solver concentrating steps near t=1 due to stiffening velocity fields.