Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
This addresses the need for virtual environment generation in applications like robotics and gaming, offering a novel approach that eliminates dependency on captured multi-view data.
The paper tackles the problem of generating 3D scenes without requiring real-world multi-view data by distilling implicit 3D knowledge from video diffusion models into an explicit 3D Gaussian Splatting representation, achieving state-of-the-art performance in static and dynamic 3D scene generation.
The ability to generate virtual environments is crucial for applications ranging from gaming to physical AI domains such as robotics, autonomous driving, and industrial AI. Current learning-based 3D reconstruction methods rely on the availability of captured real-world multi-view data, which is not always readily available. Recent advancements in video diffusion models have shown remarkable imagination capabilities, yet their 2D nature limits the applications to simulation where a robot needs to navigate and interact with the environment. In this paper, we propose a self-distillation framework that aims to distill the implicit 3D knowledge in the video diffusion models into an explicit 3D Gaussian Splatting (3DGS) representation, eliminating the need for multi-view training data. Specifically, we augment the typical RGB decoder with a 3DGS decoder, which is supervised by the output of the RGB decoder. In this approach, the 3DGS decoder can be purely trained with synthetic data generated by video diffusion models. At inference time, our model can synthesize 3D scenes from either a text prompt or a single image for real-time rendering. Our framework further extends to dynamic 3D scene generation from a monocular input video. Experimental results show that our framework achieves state-of-the-art performance in static and dynamic 3D scene generation.