CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
This addresses the challenge of generating dynamic 3D scenes from limited video input for applications in computer vision and graphics, representing an incremental advancement in 4D reconstruction methods.
The paper tackles the problem of creating 4D (dynamic 3D) scenes from monocular video by introducing CAT4D, which uses a multi-view video diffusion model and a novel sampling approach to transform single videos into multi-view videos for robust 4D reconstruction, achieving competitive performance on benchmarks.
We present CAT4D, a method for creating 4D (dynamic 3D) scenes from monocular video. CAT4D leverages a multi-view video diffusion model trained on a diverse combination of datasets to enable novel view synthesis at any specified camera poses and timestamps. Combined with a novel sampling approach, this model can transform a single monocular video into a multi-view video, enabling robust 4D reconstruction via optimization of a deformable 3D Gaussian representation. We demonstrate competitive performance on novel view synthesis and dynamic scene reconstruction benchmarks, and highlight the creative capabilities for 4D scene generation from real or generated videos. See our project page for results and interactive demos: https://cat-4d.github.io/.