新方法从冻结视频模型中提取3D运动

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-05 04:00

研究人员开发了一种名为“寄生协同去噪”的新方法，用于从冻结的文本到视频扩散模型中提取显式的3D人体运动生成。该方法利用这些模型中已有的隐式运动知识，而不是训练一个单独的运动生成器。寄生运动解码器（PMD）通过在去噪过程中读取主机模型的中间特征来高效解码运动，而主机模型保持不变。该方法实现了强大的文本-运动对齐，且可训练参数比专用运动生成器少得多，并能同时生成配对的视频和运动。 AI

影响能够从现有视频模型中提取3D运动数据，可能减少对专用运动数据集的需求。

排序理由详细介绍AI模型新能力的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍AI模型新能力的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 3 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Yunjiao Zhou, Junlang Qian, Lihua Xie, Jianfei Yang · 2026-10-05 04:00

Parasitic Co-Denoising: Unlocking 3D Human Motion Generation in a Frozen Video Diffusion Model

arXiv:2610.03047v1 Announce Type: new Abstract: Despite never being supervised on explicit 3D motion, large-scale text-to-video diffusion models synthesize realistic human motion in their generated videos. We ask whether this implicit knowledge can be turned into explicit 3D moti…

本文如何被排名

报道来源 [1]

Parasitic Co-Denoising: Unlocking 3D Human Motion Generation in a Frozen Video Diffusion Model

相关实体

相关话题