高斯似曾相识：创建具有增强泛化与个性化能力的可控3D高斯头部化身
Gaussian Deja-vu: Creating Controllable 3D Gaussian Head-Avatars with Enhanced Generalization and Personalization Abilities
AI总结：
提出高斯似曾相识框架，先用大型2D数据集训练泛化模型，再通过可学习的表情感知校正混合贴图个性化，实现快速、高质量的可控3D高斯头部化身生成。
摘要：
近年来，三维高斯泼溅（3D Gaussian Splatting, 3DGS）技术的进展为建模3D头部化身释放了巨大潜力，相比基于网格的方法提供了更大的灵活性，并且与基于NeRF的方法相比具有更高效的渲染性能。尽管有这些进展，创建可控的基于3DGS的头部化身仍然耗时，通常需要几十分钟到几个小时。为了加速这一过程，我们在此引入“高斯似曾相识”（Gaussian Deja-vu）框架，该框架首先获得头部化身的泛化模型，然后对结果进行个性化。泛化模型在大型2D（合成和真实）图像数据集上训练。该模型提供了一个初始化良好的3D高斯头部，随后使用单目视频进行细化以获得个性化的头部化身。对于个性化，我们提出了可学习的、与表情感知的校正混合贴图（rectification blendmaps）来修正初始3D高斯，确保快速收敛而不依赖神经网络。实验表明，所提出的方法达到了其目标。它在照片级真实感质量上优于最先进的3D高斯头部化身，并将训练时间消耗减少到现有方法的至少四分之一，在几分钟内生成化身。
英文摘要：
Recent advancements in 3D Gaussian Splatting (3DGS) have unlocked significant potential for modeling 3D head avatars, providing greater flexibility than mesh-based methods and more efficient rendering compared to NeRF-based approaches. Despite these advancements, the creation of controllable 3DGS-based head avatars remains time-intensive, often requiring tens of minutes to hours. To expedite this process, we here introduce the "Gaussian Deja-vu" framework, which first obtains a generalized model of the head avatar and then personalizes the result. The generalized model is trained on large 2D (synthetic and real) image datasets. This model provides a well-initialized 3D Gaussian head that is further refined using a monocular video to achieve the personalized head avatar. For personalizing, we propose learnable expression-aware rectification blendmaps to correct the initial 3D Gaussians, ensuring rapid convergence without the reliance on neural networks. Experiments demonstrate that the proposed method meets its objectives. It outperforms state-of-the-art 3D Gaussian head avatars in terms of photorealistic quality as well as reduces training time consumption to at least a quarter of the existing methods, producing the avatar in minutes.
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。
