Oct 12, 2022 � Abstract:Denoising diffusion models (DDMs) have shown promising results in 3D point cloud synthesis. To advance 3D DDMs and make them useful�...

We introduce the Latent Point Diffusion Model (LION), a DDM for 3D shape generation. LION focuses on learning a 3D generative model directly from geometry data�...

the idea is that we take the encoder and decoder trained on the data as usual (without conditioning input), and when training the diffusion prior, we feed the�...

We introduce the Latent Point Diffusion Model (LION) for 3D shape generation (see Fig. 1). Similar to previous 3D DDMs, LION operates on point clouds, but it is�...

Jun 7, 2023 � The art of generative modeling for 3D shapes has been an active research area and finds extensive applications in 3D content creation.

Oct 12, 2022 � The hierarchical Latent Point Diffusion Model (LION) is introduced, set up as a variational autoencoder (VAE) with a hierarchical latent�...

To this end, we introduce the hierarchical Latent Point Diffusion Model (LION) for 3D shape generation. LION is set up as a variational autoencoder (VAE) with a�...

LION: Latent Point Diffusion Models for 3D Shape Generation. Xiaohui Zeng, Arash Vahdat, Francis Williams, Zan Gojcic, Or Litany, Sanja Fidler,�...

Oct 14, 2022 � LION: Latent Point Diffusion Models for 3D Shape Generation abs: https://arxiv.org/abs/2210.06978 project page: https://nv-tlabs.github.io/LION/.