将你的肖像带入三维临场感
Bringing Your Portrait to 3D Presence
Dual-UV 表示把图像特征映射到规范 UV 空间以消除姿态与构图引起的词元漂移，这一思路可直接迁移到任何需要姿态不变特征的单图人体/人脸重建管线；其因子化合成数据流形（2D 生成多样性 + 3D 几何一致渲染）也为缺乏 3D 标注的化身训练提供了可复用的数据构造方案。
原文依据 We introduce a Dual-UV representation that maps image features to a canonical UV space via Core-UV and Shell-UV branches
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出了一个统一框架，可从单张肖像重建可驱动的三维人体化身，覆盖头部、半身与全身输入。该方法针对三个瓶颈：对姿态与构图敏感的特征表示、可扩展数据有限，以及代理网格估计不可靠。我们引入 Dual-UV 表示，通过 Core-UV 与 Shell-UV 两个分支将图像特征映射到规范 UV 空间，从而消除由姿态与构图引起的词元漂移。我们还构建了一个因子化合成数据流形，将二维生成多样性同几何一致的三维渲染相结合，并配套一个提升真实感与身份一致性的训练方案。一个鲁棒的代理网格跟踪器在部分可见条件下保持稳定。这些组件共同带来了强大的野外泛化能力。仅在半身合成数据上训练，我们的模型在头部与上半身重建上达到最优水平，全身结果也具竞争力。大量实验与分析进一步验证了该方法的有效性。
英文原文摘要 1054 字符
We present a unified framework for reconstructing animatable 3D human avatars from a single portrait across head, half-body, and full-body inputs. Our method tackles three bottlenecks: pose- and framing-sensitive feature representations, limited scalable data, and unreliable proxy-mesh estimation. We introduce a Dual-UV representation that maps image features to a canonical UV space via Core-UV and Shell-UV branches, eliminating pose- and framing-induced token shifts. We also build a factorized synthetic data manifold combining 2D generative diversity with geometry-consistent 3D renderings, supported by a training scheme that improves realism and identity consistency. A robust proxy-mesh tracker maintains stability under partial visibility. Together, these components enable strong in-the-wild generalization. Trained only on half-body synthetic data, our model achieves state-of-the-art head and upper-body reconstruction and competitive full-body results. Extensive experiments and analyses further validate the effectiveness of our approach.