研究人员推出 HumanSplatHMR，一个从视频中联合优化三维人体姿态估计和化身创建的新框架。该方法通过将姿态精炼与可微分渲染相结合，解决了现有方法的局限性，从而能够为新视角和新姿态生成更准确、更具泛化性的化身。该系统利用姿态估计器的人体网格估计，并通过可微分渲染器反向传播损失以精炼姿态参数，从而提高真实场景中的对齐和渲染质量。 AI
影响 该方法可以提高虚拟现实和动作捕捉应用中数字替身的真实感和准确性。
排序理由 这是一篇详细介绍人体化身创建新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.02784v1 Announce Type: new Abstract: Accurately recovering human pose and appearance from video is an essential component of scene reconstruction, with applications to motion capture, motion prediction, virtual reality, and digital twinning. Despite significant interes…
Accurately recovering human pose and appearance from video is an essential component of scene reconstruction, with applications to motion capture, motion prediction, virtual reality, and digital twinning. Despite significant interest in building realistic human avatars from video…