GAUDI: A Neural Architect for Immersive 3D Scene Generation
This addresses the challenge of immersive 3D scene generation for applications like virtual reality and content creation, representing a significant advancement beyond previous single-object methods.
The paper tackles the problem of generating complex and realistic 3D scenes that can be rendered from moving cameras, achieving state-of-the-art performance in unconditional generation across multiple datasets and enabling conditional generation from sparse images or text.
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.