Timezone: »

 
Spotlight
3DILG: Irregular Latent Grids for 3D Generative Modeling
Biao Zhang · Matthias Niessner · Peter Wonka

Tue Dec 06 05:00 PM -- 07:00 PM (PST) @
in Lightning Talks 2A-3 »

We propose a new representation for encoding 3D shapes as neural fields. The representation is designed to be compatible with the transformer architecture and to benefit both shape reconstruction and shape generation. Existing works on neural fields are grid-based representations with latents being defined on a regular grid. In contrast, we define latents on irregular grids which facilitates our representation to be sparse and adaptive. In the context of shape reconstruction from point clouds, our shape representation built on irregular grids improves upon grid-based methods in terms of reconstruction accuracy. For shape generation, our representation promotes high-quality shape generation using auto-regressive probabilistic models. We show different applications that improve over the current state of the art. First, we show results of probabilistic shape reconstruction from a single higher resolution image. Second, we train a probabilistic model conditioned on very low resolution images. Third, we apply our model to category-conditioned generation. All probabilistic experiments confirm that we are able to generate detailed and high quality shapes to yield the new state of the art in generative 3D shape modeling.

Keywords: generative modeling · shape generation · shape reconstruction · probabilistic shape reconstruction from a single image · shape representation

Author Information

Biao Zhang (KAUST)
Matthias Niessner (Technical University of Munich)
Peter Wonka (KAUST)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors