4DNeX: Feed-Forward 4D Generative Modeling Made Easy

Zhaoxi Chen^1*  Tianqi Liu^1*  Long Zhuo^2*  Jiawei Ren¹ 
Zeng Tao²  He Zhu²  FangZhou Hong¹  Liang Pan^2†  Ziwei Liu^1†

¹Nanyang Technological University  ²Shanghai AI Laboratory

^*Equal Contribution  ^†Corresponding Authors

TL;DR: 4DNeX is a feed-forward framework for generating 4D scene representations from a single image by fine-tuning a video diffusion model. It produces high-quality dynamic point clouds and enables downstream tasks such as novel-view video synthesis with strong generalizability.

teaser.mp4

🌟 Abstract

We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on computationally intensive optimization or require multi-frame video inputs, 4DNeX enables efficient, end-to-end image-to-4D generation by fine-tuning a pretrained video diffusion model. Specifically, 1) To alleviate the scarcity of 4D data, we construct 4DNeX-10M, a large-scale dataset with high-quality 4D annotations generated using advanced reconstruction approaches. 2) We introduce a unified 6D video representation that jointly models RGB and XYZ sequences, facilitating structured learning of both appearance and geometry. 3) We propose a set of simple yet effective adaptation strategies to repurpose pretrained video diffusion models for the 4D generation task. 4DNeX produces high-quality dynamic point clouds that enable novel-view video synthesis. Extensive experiments demonstrate that 4DNeX achieves competitive performance compared to existing 4D generation approaches, offering a scalable and generalizable solution for single-image-based 4D scene generation.

📚 Citation

If you find our work useful for your research, please consider citing our paper:

@article{chen20254dnex,
    title={4DNeX: Feed-Forward 4D Generative Modeling Made Easy},
    author={Chen, Zhaoxi and Liu, Tianqi and Zhuo, Long and Ren, Jiawei and Tao, Zeng and Zhu, He and Hong, Fangzhou and Pan, Liang and Liu, Ziwei},
    journal={arXiv preprint arXiv:2508.13154},
    year={2025}
}