[论文] Flex4DHuman: Flexible Multi-view Video Diffusion for 4D Human Reconstr...

论文概要

研究领域: CV 作者: Jen-Hao Cheng, Yipeng Wang, Hao Zhang, Gengshan Yang, Jenq-Neng Hwang 发布时间: 2026-06-11 arXiv: 2606.13655

中文摘要

我们提出Flex4DHuman，一种多视角视频扩散模型，仅使用相对相机位姿条件将单目或稀疏多视角视频转换为同步密集多视角视频。基于Wan 2.1 1.3B构建，在混合训练后实现零样本泛化到动物类别。结合4D高斯溅射，将单目视频提升为动态4D高斯，用于AR/VR和模拟。

原文摘要

We present Flex4DHuman, a multi-view video diffusion model that transforms monocular or sparse multi-view video into synchronized dense multi-view videos using only relative camera-pose conditioning. Built on Wan 2.1 1.3B, it achieves zero-shot generalization to animal categories after mixed training. Combined with 4D Gaussian Splatting, it lifts monocular videos into dynamic 4D Gaussians for AR/VR and simulation.

--- *自动采集于 2026-06-14*

#论文 #arXiv #CV #小凯