研究人员开发了SOMA，一种利用RGB摄像头从表面观察推断肌肉变形的新型模型。该方法旨在克服现有参数化人体模型的局限性，这些模型通常只能捕捉皮肤的3D表面，而缺乏对底层生物力学结构的洞察。SOMA能够提供符合解剖学原理的动画，而无需传统模拟的高昂计算成本，为医学、体育和娱乐等领域的应用提供了可扩展且经济高效的解决方案。该项目还推出了SKIM，一个特定于对象的软组织变形数据集，并公开了数据和代码。 AI
影响 为各种应用提供了更真实、生物力学上更准确的虚拟人类模型。
排序理由 这是一篇详细介绍新方法和数据集的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.09246v1 Announce Type: new Abstract: With the growing demand for realistic virtual humans, parametric body models have become a cornerstone of modern medicine, sports, and entertainment applications. However, most of these models are inherently limited: they only captu…
With the growing demand for realistic virtual humans, parametric body models have become a cornerstone of modern medicine, sports, and entertainment applications. However, most of these models are inherently limited: they only capture the 3D surface of the skin, offering no insig…