L3DG: Latent 3D Gaussian Diffusion
This addresses the challenge of scalable and high-quality 3D scene generation for applications like virtual reality or gaming, though it builds incrementally on existing diffusion and 3D Gaussian techniques.
The authors tackled the problem of generative 3D modeling by proposing L3DG, a latent diffusion approach for 3D Gaussians, enabling efficient room-scale scene generation with real-time rendering and improved visual quality over prior methods.
We propose L3DG, the first approach for generative 3D modeling of 3D Gaussians through a latent 3D Gaussian diffusion formulation. This enables effective generative 3D modeling, scaling to generation of entire room-scale scenes which can be very efficiently rendered. To enable effective synthesis of 3D Gaussians, we propose a latent diffusion formulation, operating in a compressed latent space of 3D Gaussians. This compressed latent space is learned by a vector-quantized variational autoencoder (VQ-VAE), for which we employ a sparse convolutional architecture to efficiently operate on room-scale scenes. This way, the complexity of the costly generation process via diffusion is substantially reduced, allowing higher detail on object-level generation, as well as scalability to large scenes. By leveraging the 3D Gaussian representation, the generated scenes can be rendered from arbitrary viewpoints in real-time. We demonstrate that our approach significantly improves visual quality over prior work on unconditional object-level radiance field synthesis and showcase its applicability to room-scale scene generation.