| title | Gen4P: Video Generators are 4D Perceivers |
|---|---|
| authors | Yitong Xia, Zeren Jiang, Chuanxia Zheng |
| date | 2026-10-15 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.22371 |
| upvotes | 7 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | We introduce Gen4P, a unified framework for recovering 4D geometry and motion from monocular video. We show that a pretrained video generator can be repurposed into a feed-forward 4D perceiver without iterative denoising. Building on on-demand querying, Gen4P processes clean video latents in a single encoder pass and predicts the requested 4D attributes through a lightweight cross-attention decoder. The on-demand query formulation enables flexible spatial sampling, and our proposed continuous-time queries further provide temporal flexibility. To strengthen geometric knowledge, we propose a straightforward plug-in solution by incorporating a pretrained video-depth LoRA as a frozen geometry prior, improving overall performance without adding extra trainable parameters. Gen4P achieves state-of-the-art or competitive performance on tasks of 3D point tracking, video depth and camera pose estimation. Qualitative results on in-the-wild videos illustrate its capability of tracking complex motion while maintaining the delicate structure. Together, these results demonstrate the potential of video generative pretraining for unified 4D perception. See https://gen4p.github.io for more visual results. |
cite
@misc{xia2026gen,
title={Gen4P: Video Generators are 4D Perceivers},
author={Yitong Xia and Zeren Jiang and Chuanxia Zheng},
year={2026},
eprint={2610.22371},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.22371}
}