English(EN) PoseRieFlow: Riemannian Flow Matching for Whole-Body Text-to-Pose Generation

PoseRieFlow框架从文本生成详细的3D人体姿态

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-09 05:00

研究人员开发了PoseRieFlow，一个用于从文本描述生成全身3D人体姿态的新颖框架。与以往经常忽略手部关节或在欧几里得空间中建模旋转的先前方法不同，PoseRieFlow直接在SMPL-H关节旋转的复杂流形上运行。该方法利用Diffusion Transformer高效处理身体部位，为手部分配特定标记以提高细节和运动学精度。该框架体积小巧，仅有2160万个参数，并在全身运动学误差的PoseScript基准测试中取得了最先进的成果，优于现有生成手部姿态的方法。 AI

影响该新框架通过实现更准确、更详细的文本到姿态生成，有望推动动画、虚拟现实和动作捕捉等领域的应用。

排序理由该集群包含一篇详细介绍新型3D人体姿态生成模型的学术论文。[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: 16 / 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新型3D人体姿态生成模型的学术论文。[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: 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.CV TIER_1 English(EN) · Jan Spindler, Bardia Ardakanian, Patrick Stotko, Reinhard Klein · 2026-11-09 05:00

PoseRieFlow：用于全身文本到姿态生成的黎曼流匹配

arXiv:2611.09692v1 Announce Type: new Abstract: We present PoseRieFlow, a compact flow-matching framework for text-conditioned generation of whole-body 3D human poses. Prior text-to-pose methods either neglect articulated hands or model rotations in Euclidean space despite their …

本文如何被排名

报道来源 [1]

PoseRieFlow：用于全身文本到姿态生成的黎曼流匹配

相关实体

相关话题