研究人员推出HAT-4D，一个新颖的代理框架，旨在从单个单目视频中重建多个物体的3D几何、时间动态和物理交互。该方法集成了视觉语言模型（VLM）和人类在回路反馈机制，以克服多物体场景中的深度歧义和遮挡等挑战。HAT-4D旨在作为具身AI和训练VLA的可扩展数据引擎，并已用于创建MVOIK-4D，一个用于单目4D交互重建的新基准。 AI
影响 通过从单个视频中重建复杂的物体交互，从而能够更有效地为具身AI和VLA训练收集数据。
排序理由 该集群描述了一篇详细介绍用于视频4D重建的新颖框架和基准的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.28215v1 Announce Type: cross Abstract: Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs. However, existing monocular 4D reconstruction method…
Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs. However, existing monocular 4D reconstruction methods primarily focus on isolated objects, often faili…