rPPG-VQA：面向无监督rPPG训练的视频质量评估框架
rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training
提出面向rPPG训练的视频质量评估框架，结合信号级SNR共识估计与场景级MLLM干扰识别，并利用质量分数进行两阶段自适应采样筛选训练数据，可直接用于提升无监督rPPG模型在野生视频上的训练效果。
原文依据 we propose rPPG-VQA, a novel framework for assessing video suitability for rPPG
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论无监督远程光电容积脉搏波（rPPG）有望利用无标注视频数据，但其潜力受到一个关键挑战的制约：在低质量的“野生”视频上训练会严重降低模型性能。这里缺失的一个关键步骤是在将视频用于rPPG模型学习之前，评估这些视频对rPPG模型训练的适用性。现有的视频质量评估（VQA）方法主要针对人类感知设计，无法直接用于上述目的。在本工作中，我们提出了rPPG-VQA，一个用于评估视频对rPPG适用性的新框架。我们整合了信号级和场景级分析，并设计了一个双分支评估架构。信号级分支通过稳健的信噪比（SNR）估计与多方法共识机制来评估视频的生理信号质量，场景级分支则使用多模态大语言模型（MLLM）来识别运动和不稳定光照等干扰。此外，我们提出了一种两阶段自适应采样（TAS）策略，利用质量分数来筛选最优训练数据集。实验表明，通过在我们框架筛选后的大规模“野生”视频上进行训练，我们可以开发出无监督rPPG模型，在标准基准上取得显著的准确性提升。我们的代码可在https://github.com/Tianyang-Dai/rPPG-VQA获取。
英文原文摘要 1416 字符
Unsupervised remote photoplethysmography (rPPG) promises to leverage unlabeled video data, but its potential is hindered by a critical challenge: training on low-quality "in-the-wild" videos severely degrades model performance. An essential step missing here is to assess the suitability of the videos for rPPG model learning before using them for the task. Existing video quality assessment (VQA) methods are mainly designed for human perception and not directly applicable to the above purpose. In this work, we propose rPPG-VQA, a novel framework for assessing video suitability for rPPG. We integrate signal-level and scene-level analyses and design a dual-branch assessment architecture. The signal-level branch evaluates the physiological signal quality of the videos via robust signal-to-noise ratio (SNR) estimation with a multi-method consensus mechanism, and the scene-level branch uses a multimodal large language model (MLLM) to identify interferences like motion and unstable lighting. Furthermore, we propose a two-stage adaptive sampling (TAS) strategy that utilizes the quality score to curate optimal training datasets. Experiments show that by training on large-scale, "in-the-wild" videos filtered by our framework, we can develop unsupervised rPPG models that achieve a substantial improvement in accuracy on standard benchmarks. Our code is available at https://github.com/Tianyang-Dai/rPPG-VQA.