chenguolin
/

MoVieS

Model card Files Files and versions

[CVPR 2026] MoVieS

This HuggingFace🤗 repo stores the pretrained model checkpoint for the CVPR 2026 paper: "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second".

For more details about usage, please refer to the official GitHub repo.

Project page: https://chenguolin.github.io/projects/MoVieS
Code: https://github.com/chenguolin/MoVieS
Paper: https://arxiv.org/abs/2507.10065 or https://huggingface.co/papers/2507.10065

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for chenguolin/MoVieS

Base model

facebook/VGGT-1B

Finetuned

(4)

this model

Paper for chenguolin/MoVieS

MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second

Paper • 2507.10065 • Published Jul 14, 2025 • 25