FlexAvatar：以部分监督学习完整三维头部化身
FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision
用可学习的 bias sink token 把单目视频与多视图数据放进同一个 Transformer 统一训练，解耦驱动信号与目标视角，从而在推理时同时获得单目数据的泛化性和多视图监督的三维完整性；这套「数据源 token」思路可迁移到其他受限于多视图稀缺的三维重建/化身任务。
原文依据 a transformer-based 3D portrait animation model with learnable data source tokens, so-called bias sinks
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 FlexAvatar，一种从单张图像创建高质量且完整的三维头部化身的方法。核心挑战在于多视图数据有限，以及单目训练往往导致不完整的三维头部重建。我们将该问题的根源归结为：从单目视频学习时，驱动信号与目标视角之间存在纠缠。为此，我们提出一种基于 Transformer 的三维肖像动画模型，并引入可学习的数据源 token，称为 bias sink，从而支持在单目与多视图数据集上进行统一训练。该设计在推理时兼取两类数据源之长：来自单目数据的强泛化能力，以及来自多视图监督的完整三维完整性。此外，我们的训练过程产生了一个平滑的潜变量化身空间，便于进行身份插值，并灵活拟合任意数量的输入观测。在单视图、少样本与单目化身创建任务上的大量评估中，我们验证了 FlexAvatar 的有效性。许多现有方法在视角外推上表现不佳，而 FlexAvatar 能生成具有逼真面部动画的完整三维头部化身。
英文原文摘要 1227 字符
We introduce FlexAvatar, a method for creating high-quality and complete 3D head avatars from a single image. A core challenge lies in the limited availability of multi-view data and the tendency of monocular training to yield incomplete 3D head reconstructions. We identify the root cause of this issue as the entanglement between driving signal and target viewpoint when learning from monocular videos. To address this, we propose a transformer-based 3D portrait animation model with learnable data source tokens, so-called bias sinks, which enables unified training across monocular and multi-view datasets. This design leverages the strengths of both data sources during inference: strong generalization from monocular data and full 3D completeness from multi-view supervision. Furthermore, our training procedure yields a smooth latent avatar space that facilitates identity interpolation and flexible fitting to an arbitrary number of input observations. In extensive evaluations on single-view, few-shot, and monocular avatar creation tasks, we verify the efficacy of FlexAvatar. Many existing methods struggle with view extrapolation while FlexAvatar generates complete 3D head avatars with realistic facial animations.