Timezone: »

 
Poster
NeRF-VAE: A Geometry Aware 3D Scene Generative Model
Adam Kosiorek · Heiko Strathmann · Daniel Zoran · Pol Moreno · Rosalia Schneider · Sona Mokra · Danilo J. Rezende

Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @
in Poster Session 1 »

We propose NeRF-VAE, a 3D scene generative model that incorporates geometric structure via Neural Radiance Fields (NeRF) and differentiable volume rendering. In contrast to NeRF, our model takes into account shared structure across scenes, and is able to infer the structure of a novel scene---without the need to re-train---using amortized inference. NeRF-VAE's explicit 3D rendering process further contrasts previous generative models with convolution-based rendering which lacks geometric structure. Our model is a VAE that learns a distribution over radiance fields by conditioning them on a latent scene representation. We show that, once trained, NeRF-VAE is able to infer and render geometrically-consistent scenes from previously unseen 3D environments of synthetic scenes using very few input images. We further demonstrate that NeRF-VAE generalizes well to out-of-distribution cameras, while convolutional models do not. Finally, we introduce and study an attention-based conditioning mechanism of NeRF-VAE's decoder, which improves model performance.

Keywords: Generative Models

Author Information

Adam Kosiorek (DeepMind)
Heiko Strathmann (Deepmind)
Daniel Zoran (DeepMind)
Pol Moreno (Google DeepMind)
Rosalia Schneider (DeepMind)
Sona Mokra (Deepmind)
Danilo J. Rezende (DeepMind)
Danilo J. Rezende

Danilo is a Senior Staff Research Scientist at Google DeepMind, where he works on probabilistic machine reasoning and learning algorithms. He has a BA in Physics and MSc in Theoretical Physics from Ecole Polytechnique (Palaiseau – France) and from the Institute of Theoretical Physics (SP – Brazil) and a Ph.D. in Computational Neuroscience at Ecole Polytechnique Federale de Lausanne, EPFL (Lausanne – Switzerland). His research focuses on scalable inference methods, generative models of complex data (such as images and video), applied probability, causal reasoning and unsupervised learning for decision-making.

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

More from the Same Authors