Skip to content
Hot eventLive

寄生协同去噪:冻结视频扩散模型中的3D人体动作生成

1 reports1 sources16 hr ago updated

Get the story

AI overview

2026年10月5日,arXiv Computer Vision(一手)报道了一项提出“寄生协同去噪”(parasitic co-denoising)范式的研究。该研究让3D人体动作沿宿主模型Wan2.1的去噪调度被解码,而非由独立动作生成器产生,从而在冻结的视频扩散模型中实现3D人体动作生成。目前公开信息仅包含该方法的基本思路,尚无实验数据、对比结果或代码开源等进一步细节。

Generated from reports · updated 16 hr ago

Timeline

Follow the coverage from different angles.

Oct 5, 2026
  1. arXiv · Computer Vision
    寄生协同去噪:解锁冻结视频扩散模型中的 3D 人体动作生成

    研究提出寄生协同去噪(parasitic co-denoising)范式,让 3D 动作沿宿主模型 Wan2.1 的去噪调度被解码,而非由独立动作生成器产生。

Heat trend

Current heat 7·Comparable peak 10(Oct 5)·Comparable change over 24 hours –

02.557.510Oct5Oct5Oct5Oct6

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.