NeuralField-LDM: Scene Generation with Hierarchical Latent Diffusion Models
| Autor: | Kim, Seung Wook, Brown, Bradley, Yin, Kangxue, Kreis, Karsten, Schwarz, Katja, Li, Daiqing, Rombach, Robin, Torralba, Antonio, Fidler, Sanja |
|---|---|
| Rok vydání: | 2023 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | 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. Comment: CVPR 2023 |
| Databáze: | arXiv |
| Externí odkaz: |
|