STAvatar: 基于软绑定与时间密度控制的单目3D头部人偶重建
STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction
AI总结：
STAvatar通过软绑定与时间密度控制方法，实现了单目视频中高保真3D头部人偶的重建，尤其在细粒度细节和遮挡区域的重建上表现优异。
摘要：
从单目视频中重建高保真且可动画化的3D头部人偶仍是一个具有挑战性但至关重要的任务。现有基于3D高斯点散布的方法通常将高斯点绑定到网格三角形，并且仅通过线性混合皮肤技术来建模变形，这导致了刚性运动和有限的表达能力。此外，它们缺乏专门策略来处理频繁遮挡的区域（例如，嘴巴内部、眼睑）。为了解决这些限制，我们提出了STAvatar，它包含两个关键组件：（1）一个UV自适应软绑定框架，利用基于图像和几何的先验知识，学习每个高斯点的特征偏移量，这在UV空间中进行。这种UV表示支持动态重采样，确保与自适应密度控制（ADC）的完全兼容，并增强对形状和纹理变化的适应性。（2）一个时间ADC策略，首先聚类结构相似的帧，以促进更精确的密度标准计算。它进一步引入了一种新的融合感知误差作为克隆标准，以共同捕捉几何和纹理差异，鼓励在需要更精细细节的区域进行密集化。在四个基准数据集上的广泛实验表明，STAvatar在重建性能方面达到了最先进的水平，特别是在捕捉细粒度细节和重建频繁遮挡区域方面。
英文摘要：
Reconstructing high-fidelity and animatable 3D head avatars from monocular videos remains a challenging yet essential task. Existing methods based on 3D Gaussian Splatting typically bind Gaussians to mesh triangles and model deformations solely via Linear Blend Skinning, which results in rigid motion and limited expressiveness. Moreover, they lack specialized strategies to handle frequently occluded regions (e.g., mouth interiors, eyelids). To address these limitations, we propose STAvatar, which consists of two key components: (1) a UV-Adaptive Soft Binding framework that leverages both image-based and geometric priors to learn per-Gaussian feature offsets within the UV space. This UV representation supports dynamic resampling, ensuring full compatibility with Adaptive Density Control (ADC) and enhanced adaptability to shape and textural variations. (2) a Temporal ADC strategy, which first clusters structurally similar frames to facilitate more targeted computation of the densification criterion. It further introduces a novel fused perceptual error as clone criterion to jointly capture geometric and textural discrepancies, encouraging densification in regions requiring finer details. Extensive experiments on four benchmark datasets demonstrate that STAvatar achieves state-of-the-art reconstruction performance, especially in capturing fine-grained details and reconstructing frequently occluded regions.
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。
