Diffusion probabilistic fashions have shortly turn out to be a significant strategy for generative modeling of photos, 3D geometry, video and different domains. Nevertheless, to adapt diffusion generative modeling to those domains the denoising community must be fastidiously designed for every area independently, oftentimes underneath the idea that information lives in an Euclidean grid. On this paper we introduce Diffusion Probabilistic Fields (DPF), a diffusion mannequin that…
See paper particulars