发表机构
The Hong Kong University of Science and Technology; Zhuoyu Technology（香港科技大学; 卓誉科技）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对相机控制视频生成中现有位置编码的尺度相关失效问题，提出 MeRoPE 编码，在 nuScenes、PanShot 数据集上实现了更强的相机运动控制一致性。
AI 中文摘要
在相机控制视频生成中，感知几何的位置编码会基于相机外参和逐像素观测光线来对 token 进行条件约束。然而，现有方案在真实世界的度量相机轨迹上存在与尺度相关的失效模式：齐次投影编码会导致注意力 logits 和特征范数随物理平移基线无限制增长。我们提出 MeRoPE（Metric Rotary Position Embedding，度量旋转位置嵌入），一种用于注意力的保范相对相机编码。MeRoPE 采用正交旋转块编码校准观测光线之间的相对方向，将原始度量位移映射为多频旋转相位，并在对极弧上添加视差锚定的对应先验。该设计严格保留特征范数，无论物理平移尺度如何都能约束 pre-softmax 注意力 logits，并保持对全局刚性坐标变化的完全不变性。在分别覆盖大基线轨迹和多样相机光学系统的 nuScenes 和 PanShot 数据集上，MeRoPE 实现了比现有编码更强的相机控制效果，生成的相机运动与条件位姿在旋转和平移上均达到最佳一致性。代码将公开可用。
英文摘要
In camera-controlled video generation, geometry-aware positional encodings condition tokens on camera extrinsics and per-token viewing rays. Existing schemes, however, have a scale-dependent failure mode on real-world metric camera trajectories: homogeneous projective encodings cause attention logits and feature norms to grow unbounded with physical translation baselines. We propose MeRoPE (Metric Rotary Position Embedding), a norm-preserving relative camera encoding for attention. MeRoPE encodes relative orientations between calibrated viewing rays with orthogonal rotation blocks, maps raw metric displacements into multi-frequency rotary phases, and adds a disparity-anchored correspondence prior along the epipolar arc. This design strictly preserves feature norms, bounds pre-softmax attention logits regardless of the physical translation scale, and maintains exact invariance to global rigid coordinate changes. Across nuScenes and PanShot, which cover large-baseline trajectories and diverse camera optics, respectively, MeRoPE achieves stronger camera control than prior encodings, with the best consistency between generated camera motion and conditioning poses in both rotation and translation. Code will be made publicly available.
Comments22 pages, 12 figures, and 7 tables. Project page: https://qiaozhijian.github.io/merope/
