NeRF-VAE: A Geometry Aware 3D Scene Generative Model

Abstract

We propose NeRF-VAE, a 3D scene generative model that incorporates geometric structure via 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 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.

17 pages, 15 figures, under review

References in corpus (8)

• Auto-Encoding Variational Bayes
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• A Learned Representation For Artistic Style
• NVAE: A Deep Hierarchical Variational Autoencoder
• GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
• pixelNeRF: Neural Radiance Fields from One or Few Images
• Iterative Amortized Inference
• Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes

Cited by in corpus (6)

• A survey of synthetic data augmentation methods in computer vision
• Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
• Unsupervised Discovery of Object Radiance Fields
• SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decomposition
• Neural Fields in Visual Computing and Beyond
• Learning to Stylize Novel Views