基于面部部件分割几何引导的3D人脸重建
3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation
AI总结：
针对现有3DMM人脸重建方法因监督信号不足难以处理极端表情、基于可微渲染器的分割引导方法易陷局部最优的问题，提出部件重投影距离损失PRDL，通过几何描述子优化重建，实现SOTA性能。
摘要：
3D Morphable Models（3DMM，三维形变模型）在各类应用中展现出良好的3D人脸重建效果。然而，由于稀疏或不准确的关键点等监督信号不足，现有方法难以重建带有极端表情的人脸。分割信息包含人脸重建所需的有效几何上下文。部分研究直观地依赖可微渲染器，将重建结果的渲染轮廓与分割结果进行对比，这类方法容易陷入局部最优、存在梯度不稳定等问题。本文提出部件重投影距离损失（Part Re-projection Distance Loss，PRDL），充分利用面部部件分割的几何信息。具体而言，PRDL将面部部件分割转换为2D点集，并将重建结果重投影到图像平面。随后，通过引入网格锚点并计算这些锚点到点集的不同统计距离，PRDL构建几何描述子，以优化人脸重建中点集的分布。与基于渲染器的方法相比，PRDL具有清晰的梯度，在大量定量和定性实验中取得了当前最优的重建性能。我们的项目可在https://github.com/wang-zidu/3DDFA-V3 获取。
英文摘要：
3D Morphable Models (3DMMs) provide promising 3D face reconstructions in various applications. However, existing methods struggle to reconstruct faces with extreme expressions due to deficiencies in supervisory signals, such as sparse or inaccurate landmarks. Segmentation information contains effective geometric contexts for face reconstruction. Certain attempts intuitively depend on differentiable renderers to compare the rendered silhouettes of reconstruction with segmentation, which is prone to issues like local optima and gradient instability. In this paper, we fully utilize the facial part segmentation geometry by introducing Part Re-projection Distance Loss (PRDL). Specifically, PRDL transforms facial part segmentation into 2D points and re-projects the reconstruction onto the image plane. Subsequently, by introducing grid anchors and computing different statistical distances from these anchors to the point sets, PRDL establishes geometry descriptors to optimize the distribution of the point sets for face reconstruction. PRDL exhibits a clear gradient compared to the renderer-based methods and presents state-of-the-art reconstruction performance in extensive quantitative and qualitative experiments. Our project is available at https://github.com/wang-zidu/3DDFA-V3 .
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。
