GAUDI: A Neural Architect for Immersive 3D Scene Generation

TL;DR

GAUDI is a scalable neural architecture that generates realistic 3D scenes from various inputs, advancing immersive scene rendering with state-of-the-art performance and flexible conditioning capabilities.

Contribution

It introduces a novel latent representation disentangling radiance and camera pose, enabling scalable unconditional and conditional 3D scene generation.

Findings

Achieves state-of-the-art results in unconditional 3D scene generation

Supports conditional generation from images or text

Generalizes beyond single-object models

Abstract

We introduce GAUDI, a generative model capable of capturing the distribution of complex and realistic 3D scenes that can be rendered immersively from a moving camera. We tackle this challenging problem with a scalable yet powerful approach, where we first optimize a latent representation that disentangles radiance fields and camera poses. This latent representation is then used to learn a generative model that enables both unconditional and conditional generation of 3D scenes. Our model generalizes previous works that focus on single objects by removing the assumption that the camera pose distribution can be shared across samples. We show that GAUDI obtains state-of-the-art performance in the unconditional generative setting across multiple datasets and allows for conditional generation of 3D scenes given conditioning variables like sparse image observations or text that describes the scene.