NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models
This addresses the need for efficient 3D content creation in domains such as virtual reality and robotics simulation, representing an incremental advancement by adapting 2D diffusion methods to 3D scene generation.
The paper tackles the problem of automatically generating high-quality 3D scenes for applications like virtual reality and robotics simulation by introducing NeuralField-LDM, a generative model that synthesizes complex 3D environments, achieving a substantial improvement over existing state-of-the-art models.
Automatically generating high-quality real world 3D scenes is of enormous interest for applications such as virtual reality and robotics simulation. Towards this goal, we introduce NeuralField-LDM, a generative model capable of synthesizing complex 3D environments. We leverage Latent Diffusion Models that have been successfully utilized for efficient high-quality 2D content creation. We first train a scene auto-encoder to express a set of image and pose pairs as a neural field, represented as density and feature voxel grids that can be projected to produce novel views of the scene. To further compress this representation, we train a latent-autoencoder that maps the voxel grids to a set of latent representations. A hierarchical diffusion model is then fit to the latents to complete the scene generation pipeline. We achieve a substantial improvement over existing state-of-the-art scene generation models. Additionally, we show how NeuralField-LDM can be used for a variety of 3D content creation applications, including conditional scene generation, scene inpainting and scene style manipulation.