English(EN) Triangular Resampling for Long-Horizon Motion Generation

新的三角重采样方法改进了长时程运动生成

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-02 04:00

研究人员开发了三角重采样（TR）技术，这是一种新颖的训练后技术，旨在提高运动扩散模型在长序列上的准确性。该方法通过将基于滚动的训练扩展到部分去噪状态，并使用真实值钳位来防止过度漂移，从而解决了误差累积问题。在HumanML3D数据集上的实验表明，TR在120秒运动生成任务中显著降低了误差和退化，取得了最先进的结果。 AI

影响该方法可能带来更准确、更连贯的AI生成动画和角色动作。

排序理由该集群包含一篇详细介绍运动生成新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍运动生成新方法的论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Kunhang Li, Yiyi Cai, Xiangyue Zhang, Fangyuan Tu, Yuhan Wu, Zhixiang Wang, Kaipeng Zhang, Haiyang Liu · 2026-10-02 04:00

用于长时域运动生成的三角重采样

arXiv:2609.34697v2 Announce Type: replace-cross Abstract: We introduce Triangular Resampling (TR), a post-training method for mitigating long-horizon error accumulation in motion diffusion models. Built on FloodDiffusion's triangular denoising schedule, TR addresses the mismatch …

本文如何被排名

报道来源 [1]

用于长时域运动生成的三角重采样

相关实体

相关话题