研究人员开发了4DAnyone，一个能够从单个、未校准的视频中重建三维人物模型的创新框架。该系统生成一致的多视图视频，然后将其转换为4D高斯溅射表示。为了解决众多视图之间扩展和保持一致性的挑战，4DAnyone采用了参考上下文打包来压缩参考视图，并采用目标上下文路由来促进去噪过程中不同视图组之间的信息交换。 AI
影响 能够从普通视频中更便捷、更详细地创建4D人物化身。
排序理由 该集群包含一篇详细介绍4D人物重建新方法的论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
We present 4DAnyone, a framework for reconstructing 4D humans from an uncalibrated monocular video by generating reconstruction-grade multiview-consistent videos and lifting them into 4D Gaussian Splatting (4DGS). Existing camera-controlled video diffusion models synthesize plaus…
4DAnyone reconstructs 4D humans from monocular video by generating multiview-consistent videos and lifting them into 4D Gaussian Splatting, using reference and target context designs to overcome scaling bottlenecks.
arXiv:2608.20335v1 Announce Type: new Abstract: We present 4DAnyone, a framework for reconstructing 4D humans from an uncalibrated monocular video by generating reconstruction-grade multiview-consistent videos and lifting them into 4D Gaussian Splatting (4DGS). Existing camera-co…