CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models

Rundi Wu; Ruiqi Gao; Ben Poole; Alex Trevithick; Changxi Zheng; Jonathan T. Barron; Aleksander Holynski

CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models

Computer Vision and Pattern Recognition 2024-12-20 v2

Authors: Rundi Wu , Ruiqi Gao , Ben Poole , Alex Trevithick , Changxi Zheng , Jonathan T. Barron , Aleksander Holynski

Abstract

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/.

Keywords

novel view synthesis video generation

Cite

@article{arxiv.2411.18613,
  title  = {CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models},
  author = {Rundi Wu and Ruiqi Gao and Ben Poole and Alex Trevithick and Changxi Zheng and Jonathan T. Barron and Aleksander Holynski},
  journal= {arXiv preprint arXiv:2411.18613},
  year   = {2024}
}

Comments

Project page: https://cat-4d.github.io/

CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models

Abstract

Keywords

Cite

Comments

Related papers