Probability-Flow Distillation exactly matches the Wasserstein gradient flow of the target distribution when distilling 2D diffusion priors into 3D models, yielding higher-fidelity results than SDS or SDI.
Ordinary Differential Equations
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Proves PAC consistency and explicit convergence rates for learned transport integrated (LtI) quadrature using neural ODE flows for general targets and empirical quantile maps for product targets.
Develops an evolving finite element method for parabolic PDEs with evolving interfaces, derives a suitable weak formulation, proves optimal error bounds for isoparametric elements of arbitrary order, and verifies convergence numerically.
citing papers explorer
-
Probability-Flow Distillation: Exact Wasserstein Gradient Flow for High-Fidelity 3D Generation
Probability-Flow Distillation exactly matches the Wasserstein gradient flow of the target distribution when distilling 2D diffusion priors into 3D models, yielding higher-fidelity results than SDS or SDI.
-
Consistency of Learned Sparse Grid Quadrature Rules using NeuralODEs
Proves PAC consistency and explicit convergence rates for learned transport integrated (LtI) quadrature using neural ODE flows for general targets and empirical quantile maps for product targets.
-
Evolving finite elements for advection diffusion with an evolving interface
Develops an evolving finite element method for parabolic PDEs with evolving interfaces, derives a suitable weak formulation, proves optimal error bounds for isoparametric elements of arbitrary order, and verifies convergence numerically.