EgoControl：基于3D全身姿态的可控第一人称视频生成
EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses
把显式3D全身姿态序列作为扩散模型的条件信号，并设计同时编码全局相机运动与关节体运动的姿态表示，为视觉研究者提供了一种可复用的「姿态→视频」控制接口，可用于具身智能中的动作模拟与规划。
原文依据 we propose EgoControl, a pose-controllable video diffusion model trained on egocentric data
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论通过身体运动实现细粒度控制的第一人称视频生成，是构建能够模拟、预测与规划动作的具身智能体的关键需求。在本工作中，我们提出 EgoControl，一个在第一人称数据上训练的姿态可控视频扩散模型。我们训练一个视频预测模型，以显式的3D身体姿态序列作为未来帧生成的条件。为实现精确的运动控制，我们引入一种新颖的姿态表示，它同时刻画全局相机动态与关节化的人体运动，并通过扩散过程内专门的控制机制将其注入。给定一小段观测帧序列与目标姿态序列，EgoControl 生成与所给姿态控制对齐、时序连贯且视觉真实的未来帧。实验结果表明，EgoControl 能够生成高质量、姿态一致的第一人称视频，为可控的具身视频模拟与理解开辟了道路。
英文原文摘要 998 字符
Egocentric video generation with fine-grained control through body motion is a key requirement towards embodied AI agents that can simulate, predict, and plan actions. In this work, we propose EgoControl, a pose-controllable video diffusion model trained on egocentric data. We train a video prediction model to condition future frame generation on explicit 3D body pose sequences. To achieve precise motion control, we introduce a novel pose representation that captures both global camera dynamics and articulated body movements, and integrate it through a dedicated control mechanism within the diffusion process. Given a short sequence of observed frames and a sequence of target poses, EgoControl generates temporally coherent and visually realistic future frames that align with the provided pose control. Experimental results demonstrate that EgoControl produces high-quality, pose-consistent egocentric videos, paving the way toward controllable embodied video simulation and understanding.