This page is dedicated to hosting animated samples for the paper “Unifying GANs and Score-Based Diffusion as Generative Particle Models” (Jean-Yves Franceschi, Mike Gartrell, Ludovic Dos Santos, Thibaut Issenhuth, Emmanuel de Bézenac, Mickaël Chen, Alain Rakotomamonjy), to appear at NeurIPS 2023. Cf. the paper and the code for more information.

Erratum. Equation (17) in the paper should read as:

    \[\dif x_t = - \mathbb{E}_{x'_t \sim \rho_t} \left[{k(x_t, x'_t) \nabla_{W} \mathcal{F}(\rho_t)(x'_t)\right] \dif t.\]

MNIST

EDM

Discriminator Flow


CelebA

EDM

Discriminator Flow


Gaussians

Please refer to Appendix C of the paper for a detailed description.

EDM

55 NFE
13 NFE

Discriminator Flow (inference)

56 NFE
14 NFE

GAN (training)

Score GAN (training)

Generated samples.
Noisy samples with corresponding gradients.