发布日期: 2025-11-27

更新日期: 2025-11-27

文章字数: 1.2k

阅读时长: 4 分

阅读次数:

⚠️ 以下所有内容总结都来自于大语言模型的能力，如有错误，仅供参考，谨慎使用
🔴 请注意：千万不要用于严肃的学术场景，只能用于论文阅读前的初筛！
💗 如果您觉得我们的项目对您有帮助 ChatPaperFree ，还请您给我们一些鼓励！⭐️ HuggingFace免费体验

2025-11-27 更新

STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction

Authors:Jiankuo Zhao, Xiangyu Zhu, Zidu Wang, Zhen Lei

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. The code will be publicly available.

从单目视频中重建高保真和可动画的3D头像仍然是一个具有挑战但重要的任务。现有方法通常基于3D高斯拼贴，将高斯绑定到网格三角形上，并通过线性混合蒙皮技术建模变形，这导致动作僵硬和表现力有限。此外，他们缺乏处理频繁遮挡区域的专门策略（例如嘴巴内部和上眼睑）。为了解决这些局限性，我们提出了STAvatar，它由两个关键组件组成：（1）UV自适应软绑定框架，它利用图像和几何先验知识来学习UV空间内的每个高斯特征偏移量。这种UV表示支持动态重采样，确保与自适应密度控制（ADC）完全兼容，并提高对形状和纹理变化的适应性。（2）时间ADC策略首先通过聚类结构相似帧来简化计算密集化标准的过程。它进一步引入了一种新型融合感知误差作为克隆标准，以共同捕获几何和纹理差异，鼓励在需要精细细节的区域进行密集化。在四个基准数据集上的大量实验表明，STAvatar达到了最先进的重建性能，特别是在捕捉精细细节和重建频繁遮挡区域方面。代码将公开可用。

论文及项目相关链接

PDF 17 pages, 14 figures

Summary

基于单目视频重建高保真且可动画的3D头像仍然是一个挑战但重要的任务。现有方法主要通过3D高斯拼贴技术绑定高斯到网格三角形，并通过线性混合蒙皮技术模拟变形，这导致运动僵硬和表现力有限。此外，它们缺乏处理频繁遮挡区域的特殊策略。针对这些局限性，我们提出了STAvatar系统，包括两个关键组件：一是UV自适应软绑定框架，利用图像和几何先验学习UV空间内的每个高斯特征偏移量；二是时间自适应密度控制策略，首先聚类结构相似的帧以更有效地计算稠密化标准，并引入新的融合感知误差作为克隆标准来捕捉几何和纹理差异。在四个基准数据集上的广泛实验表明，STAvatar在重建精细细节和遮挡区域方面取得了最新技术水平的性能。

Key Takeaways