在大面部角度变化下实现身份一致的视频生成
Identity-Consistent Video Generation under Large Facial-Angle Variations
AI总结：
本文提出Mv²ID框架，通过区域遮蔽训练策略和参考解耦RoPE机制，解决大角度变化下的身份一致性与自然运动平衡问题，并构建大规模数据集和评估指标。
摘要：
单视图参考到视频的方法在大面部角度变化下难以保持身份一致性。为解决此问题，本文提出Mv²ID框架，采用区域遮蔽训练策略以防止快捷学习，并提取本质身份特征。此外，设计了参考解耦RoPE机制，为视频和条件标记分配不同的位置编码以更好地建模其异质属性。同时构建了大规模数据集并提出专用评估指标。实验表明，本文方法在保持运动自然性的同时显著提升了身份一致性，优于现有基于跨配对数据训练的方法。
英文摘要：
Single-view reference-to-video methods often struggle to preserve identity consistency under large facial-angle variations. This limitation naturally motivates the incorporation of multi-view facial references. However, simply introducing additional reference images exacerbates the \textit{copy-paste} problem, particularly the \textbf{\textit{view-dependent copy-paste}} artifact, which reduces facial motion naturalness. Although cross-paired data can alleviate this issue, collecting such data is costly. To balance the consistency and naturalness, we propose $\mathrm{Mv}^2\mathrm{ID}$, a multi-view conditioned framework under in-paired supervision. We introduce a region-masking training strategy to prevent shortcut learning and extract essential identity features by encouraging the model to aggregate complementary identity cues across views. In addition, we design a reference decoupled-RoPE mechanism that assigns distinct positional encoding to video and conditioning tokens for better modeling of their heterogeneous properties. Furthermore, we construct a large-scale dataset with diverse facial-angle variations and propose dedicated evaluation metrics for identity consistency and motion naturalness. Extensive experiments demonstrate that our method significantly improves identity consistency while maintaining motion naturalness, outperforming existing approaches trained with cross-paired data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
