PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image
This addresses the challenge of creating realistic 3D models from limited input for applications in graphics and simulation, representing a novel approach in the field.
The paper tackles the problem of generating physically plausible compositional 3D assets from a single image by introducing PhyCAGE, which uses multi-view image generation, 3D Gaussian Splatting, and a Physical Simulation-Enhanced Score Distillation Sampling technique to optimize positions, resulting in physically compatible 3D assets.
We present PhyCAGE, the first approach for physically plausible compositional 3D asset generation from a single image. Given an input image, we first generate consistent multi-view images for components of the assets. These images are then fitted with 3D Gaussian Splatting representations. To ensure that the Gaussians representing objects are physically compatible with each other, we introduce a Physical Simulation-Enhanced Score Distillation Sampling (PSE-SDS) technique to further optimize the positions of the Gaussians. It is achieved by setting the gradient of the SDS loss as the initial velocity of the physical simulation, allowing the simulator to act as a physics-guided optimizer that progressively corrects the Gaussians' positions to a physically compatible state. Experimental results demonstrate that the proposed method can generate physically plausible compositional 3D assets given a single image.