研究人员开发了 PrismAvatar，一个用于实时立体通信的系统，该系统可以从单个单目视频源重建头部头像。该系统利用自然的头部运动作为伪多视角监督，以改善头发和耳朵等观察较弱区域的重建。然后，PrismAvatar 渲染多个为无眼镜透镜显示器编码的虚拟视图，使用蒸馏驱动程序实现了高达 38.49 FPS 的帧速率。 AI
影响 通过从单个视频源重建 3D 头像，实现更具沉浸感的实时通信。
排序理由 该集群包含一篇详细介绍立体通信新系统的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.10550v1 Announce Type: new Abstract: Real-time stereoscopic video communication has long been a goal of immersive telepresence, yet practical systems still require specialized capture rigs or reduce remote users to a single portrait view. We present PrismAvatar, a Gaus…
Real-time stereoscopic video communication has long been a goal of immersive telepresence, yet practical systems still require specialized capture rigs or reduce remote users to a single portrait view. We present PrismAvatar, a Gaussian head-avatar system that connects monocular …