CAT4D transforms monocular videos into dynamic 4D scenes using a multi-view video diffusion model, enabling novel view synthesis and robust scene reconstruction through a deformable 3D Gaussian representation.

https://arxiv.org/abs//2411.18613

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers