CanonicalPhys: Pose-Robust Remote Photoplethysmography via Canonical-Space Priors

TL;DR - CanonicalPhys improves camera-based heart-rate estimation under head rotation by warping facial landmarks into a canonical coordinate space. This enables anatomy-dependent physiological priors and reduces pose-related errors without adding trainable parameters.

• Uses a differentiable four-point homography to stabilize facial anatomy across poses.
• Adds Lambertian pixel weighting, cross-region temporal consistency, and POS-based knowledge distillation.
• Reduces frontal-to-large-yaw MAE degradation on MMPD from 1.60× to 1.33×.
• Achieves cross-dataset MAE reductions of up to 32% on pose-rich targets.