$\unicode{x1F493}$Heartian：生理感知的可重光照高斯头部头像
Heartian: Physiology-Aware Relightable Gaussian Head Avatar
浏览论文内容
中文总结 AI 辅助
本文提出生理感知框架Heartian，将远程光电容积脉搏波信号编码为高斯头部头像的可控材质属性，在保持重建质量的同时实现高精度心率恢复。
中文摘要 AI 辅助
高斯头部头像通常将内在的面部外观建模为时间静态的，忽略了由心脏引起的细微肤色变化。我们提出了$\unicode{x1F493}$Heartian，一个生理感知的调制框架，该框架在可重光照头部头像中学习依赖于心动周期的逐帧面部皮肤区域高斯的反照率调制，以编码远程光电容积脉搏波（rPPG）信号。利用同步接触式PPG监督，$\unicode{x1F493}$Heartian将规定的心动波形建模为两个高斯函数的和，并通过轻量级MLP学习逐帧空间残差。在来自UBFC-rPPG、PURE和MMPD的152个静态记录中，所提供信号的属性空间恢复实现了合并的记录级心率平均绝对误差（MAE）为0.29 bpm，平均绝对百分比误差（MAPE）为0.38%。渲染后，基准rPPG方法仍可检测到这些信号，最佳测试配置——在UBFC-rPPG上预训练的运动增强TS-CAN解码器——从渲染的MMPD头像中恢复心率，MAE为0.97 bpm，MAPE为1.21%。同时，$\unicode{x1F493}$Heartian保持了与基线相当的重建质量，平均PSNR仅下降0.005 dB。总体而言，我们的工作将可恢复的rPPG信号作为可控材质属性嵌入到特定主体的高斯头部头像中，同时保持重建质量。
英文摘要
Gaussian head avatars typically model intrinsic facial appearance as temporally static, omitting subtle cardiac-induced skin-color variation. We propose Heartian, a physiology-aware modulation framework that learns cardiac-cycle-dependent per-frame albedo modulation of facial skin-region Gaussians within a relightable head avatar to encode remote photoplethysmography (rPPG) signals. Using synchronized contact PPG supervision, Heartian models the prescribed cardiac waveform as the sum of two Gaussian functions and learns per-frame spatial residuals via a lightweight MLP. Across 152 stationary recordings from UBFC-rPPG, PURE, and MMPD, attribute-space recovery of the supplied signal achieves a pooled recording-level heart-rate MAE of 0.29 bpm and MAPE of 0.38%. The signals remain detectable after rendering by benchmark rPPG methods, with the best tested configuration - a motion-augmented TS-CAN decoder pretrained on UBFC-rPPG - recovering heart rate from the rendered MMPD avatars at 0.97 bpm MAE and 1.21% MAPE. Meanwhile, Heartian maintains reconstruction quality comparable to the baseline, with negligible average PSNR degradation of 0.005 dB. Overall, our work embeds recoverable rPPG signals as controllable material attributes to subject-specific Gaussian head avatars while retaining the reconstruction quality.
发表机构
- University College London（伦敦大学学院）
- Adobe Research（Adobe研究院）
- Stanford University（斯坦福大学）
机构由 AI 辅助整理，请以论文原文为准。
