CodePhys: Robust Video-based Remote Physiological Measurement through Latent Codebook Querying

TL;DR

CodePhys introduces a novel noise-robust approach for remote physiological measurement from facial videos by matching noisy signals with a ground-truth codebook, significantly improving accuracy under real-world interference.

Contribution

The paper presents CodePhys, a new method that models rPPG measurement as a code query task in a noise-free space, enhancing robustness against real-world video interference.

Findings

Outperforms state-of-the-art methods on four benchmark datasets.

Effective in both intra-dataset and cross-dataset evaluations.

Utilizes a spatial attention mechanism and distillation loss for improved signal fidelity.

Abstract

Remote photoplethysmography (rPPG) aims to measure non-contact physiological signals from facial videos, which has shown great potential in many applications. Most existing methods directly extract video-based rPPG features by designing neural networks for heart rate estimation. Although they can achieve acceptable results, the recovery of rPPG signal faces intractable challenges when interference from real-world scenarios takes place on facial video. Specifically, facial videos are inevitably affected by non-physiological factors (e.g., camera device noise, defocus, and motion blur), leading to the distortion of extracted rPPG signals. Recent rPPG extraction methods are easily affected by interference and degradation, resulting in noisy rPPG signals. In this paper, we propose a novel method named CodePhys, which innovatively treats rPPG measurement as a code query task in a noise-free proxy space (i.e., codebook) constructed by ground-truth PPG signals. We consider noisy rPPG features as queries and generate high-fidelity rPPG features by matching them with noise-free PPG features from the codebook. Our approach also incorporates a spatial-aware encoder network with a spatial attention mechanism to highlight physiologically active areas and uses a distillation loss to reduce the influence of non-periodic visual interference. Experimental results on four benchmark datasets demonstrate that CodePhys outperforms state-of-the-art methods in both intra-dataset and cross-dataset settings.