Abstract
Facial optical flow supports a wide range of tasks in facial motion analysis. However, the lack of high-resolution facial optical flow datasets has hindered progress in this area. In this paper, we introduce Splatting Rasterization Flow (SRFlow), a high-resolution facial optical flow dataset, and Splatting Rasterization Guided FlowNet (SRFlowNet), a facial optical flow model with tailored regularization losses. These losses constrain flow predictions using masks and gradients computed via difference or Sobel operator. This effectively suppresses high-frequency noise and large-scale errors in texture-less or repetitive-pattern regions, enabling SRFlowNet to be the first model explicitly capable of capturing high-resolution skin motion guided by Gaussian splatting rasterization. Experiments show that training with the SRFlow dataset improves facial optical flow estimation across various optical flow models, reducing end-point error (EPE) by up to 42% (from 0.5081 to 0.2953). Furthermore, when coupled with the SRFlow dataset, SRFlowNet achieves up to a 48% improvement in F1-score (from 0.4733 to 0.6947) on a composite of three micro-expression datasets. These results demonstrate the value of advancing both facial optical flow estimation and micro-expression recognition.
Abstract (translated)
面部光学流支持面部运动分析中的广泛任务。然而，缺乏高分辨率的面部光学流数据集阻碍了这一领域的发展。在本文中，我们介绍了Splatting Rasterization Flow (SRFlow)，这是一个高分辨率的面部光学流数据集，以及Splatting Rasterization Guided FlowNet (SRFlowNet)，这是一种专为定制正则化损失而设计的面部光学流模型。这些损失通过使用掩码和差分或Sobel算子计算的梯度来约束光流预测，从而有效地抑制了无纹理或重复图案区域中的高频噪声和大规模误差。这使得SRFlowNet成为首个能够捕捉由高斯点染光栅化引导下的高分辨率皮肤运动的模型。 实验表明，使用SRFlow数据集进行训练可以提高各种光学流模型的面部光学流估计精度，将末端点误差（EPE）最多降低42%（从0.5081降至0.2953）。此外，在与SRFlow数据集结合时，SRFlowNet在三个微表情数据集组成的综合评估中实现了高达48%的F1分数改进（从0.4733提高到0.6947）。 这些结果展示了推进面部光学流估计和微表情识别的价值。
URL
https://arxiv.org/abs/2601.06479
