WorldCast：大角度相机控制下的世界一致角色视频生成
原标题：Paper page - WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control
AI 摘要
该论文提出 WorldCast 框架与 CLACT 数据集，用于在大角度相机运动下生成世界一致的角色视频。WorldCast 利用深度估计将初始帧反投影为 3D 点云，并沿目标相机轨迹渲染以获得显式几何引导与覆盖掩码，同时引入几何对齐记忆注意力（GAMA）检索并注入视角相关的角色特征。评估显示该方法能准确跟随大角度轨迹，并保持角色几何、外观与身份一致性。
正文节选
WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control Abstract CLACT and WorldCast enable consistent character video generation under large-angle camera motions by combining 3D point-cloud guidance with geometry-aligned memory attention. Precise camera control is essential for cinematic character video generation, yet existing methods struggle to follow large-angle trajectories with combined rotation, translation, and radius variation from arbitrary initial azimu