LQ-rPPG: A Label-Quantized Coarse-to-Fine Learning Framework for Remote Physiological Measurement

• URL: http://arxiv.org/abs/2605.23174v1
• Date: Fri, 22 May 2026 02:46:11 GMT
• Title: LQ-rPPG: A Label-Quantized Coarse-to-Fine Learning Framework for Remote Physiological Measurement
• Abstract summary: LQ-r is a label-to-fine learning framework for robust r estimation.<n>It transforms continuous signals into multi-bit quantized pseudo labels with reduced noise and variability.<n>LQ-r achieves robust and general r estimation even under challenging conditions.
• Score: 9.606144267032215
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Remote photoplethysmography (rPPG) enables non-contact measurement of physiological signals from facial videos, offering strong potential for remote healthcare and daily health monitoring. Driven by this potential, various deep learning-based rPPG methods have been proposed to improve rPPG estimation. However, previous deep learning-based rPPG methods have paid little attention to the quality of training labels and their impact on model learning. Contact-based PPG signals used as training labels often contain noise and variability caused by motion artifacts, inconsistent sensor contact, and morphological distortions. Such label inconsistency can lead models to overfit to the label noise and variability and consequently degrade generalization performance. To address this issue, we propose LQ-rPPG, a label-quantized coarse-to-fine learning framework for robust rPPG estimation. LQ-rPPG consists of a label quantization module and a coarse-to-fine rPPG estimation model. The label quantization module transforms continuous PPG signals into multi-bit quantized pseudo labels with reduced noise and variability. The coarse-to-fine estimation model progressively refines rPPG signals under hierarchical supervision guided by the multi-bit pseudo labels. This design alleviates overfitting to label-specific variations and enables the model to learn structured and consistent representations. As a result, LQ-rPPG achieves robust and generalizable rPPG estimation even under challenging conditions. Experiments on multiple benchmark datasets demonstrate that LQ-rPPG achieves strong performance in both intra- and cross-dataset evaluations, while reducing parameters and multiply-accumulate operations by 88% and 29%, respectively, and increasing throughput by 191%. The code is available at https://github.com/Anonymous-repo-code/LQ-rPPG.

Related papers

• rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training [7.772569910275165]
  Unsupervised remote photoplethysmography (r) 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.<n>We propose r-VQA, a novel framework for assessing multimodal video suitability for r-VQA.<n> Experiments show that by training on large-scale, "in-the-wild" videos filtered by our framework, we can develop unsupervised r models that achieve a substantial improvement in accuracy on standard benchmarks.
  arXiv  Detail & Related papers  (2026-04-13T08:17:56Z)
• Sharpness-aware Dynamic Anchor Selection for Generalized Category Discovery [61.694524826522205]
  Given some labeled data of known classes, GCD aims to cluster unlabeled data that contain both known and unknown classes.<n>Large pre-trained models have a preference for some specific visual patterns, resulting in encoding spurious correlation for unlabeled data.<n>We propose a novel method, which contains two modules: Loss Sharpness Penalty (LSP) and Dynamic Anchor Selection (DAS)
  arXiv  Detail & Related papers  (2025-12-15T02:24:06Z)
• TYrPPG: Uncomplicated and Enhanced Learning Capability rPPG for Remote Heart Rate Estimation [51.56484100374058]
  This paper introduces an innovative video understanding block (GVB) designed for efficient RGB videos.<n>Based on the Mam structure, this block integrates 2D-CNN and 3D-CNN to enhance video understanding for analysis.<n>Experiments show that our TYr can achieve state-of-the-art performance in commonly used datasets.
  arXiv  Detail & Related papers  (2025-11-08T03:46:58Z)
• CodePhys: Robust Video-based Remote Physiological Measurement through Latent Codebook Querying [26.97093819822487]
  Remote photoplethysmography aims to measure non-contact physiological signals from facial videos.<n>Most existing methods directly extract video-based r features by designing neural networks for heart rate estimation.<n>Recent methods are easily affected by interference and degradation, resulting in noisy r signals.<n>We propose a novel method named CodePhys, which innovatively treats r measurement as a code task in a noise-free proxy space.
  arXiv  Detail & Related papers  (2025-02-11T13:05:42Z)
• Semi-rPPG: Semi-Supervised Remote Physiological Measurement with Curriculum Pseudo-Labeling [31.592892663270252]
  Photoplethysmography (r) is a promising technique to monitor physiological signals such as heart rate from facial videos.<n>Current r research is mainly based on several small public datasets collected in simple environments.<n>Semi-supervised methods that leverage a small amount of labeled data and abundant unlabelled data can fill this gap for r learning.
  arXiv  Detail & Related papers  (2025-02-06T08:16:08Z)
• DD-rPPGNet: De-interfering and Descriptive Feature Learning for Unsupervised rPPG Estimation [8.901227918730562]
  Photoplethysvolution (rmography) aims to measure physiological signals and Heart Rate (HR) from facial videos.<n>Recent unsupervised r estimation methods have shown promising potential in estimating r signals from facial regions without relying on ground truth r signals.<n>We propose a novel Deinterfered and Descriptive r Estimation Network (DD-rNet) to eliminate the interference within r features for learning genuine r signals.
  arXiv  Detail & Related papers  (2024-07-31T07:43:58Z)
• Fully Test-Time rPPG Estimation via Synthetic Signal-Guided Feature Learning [8.901227918730562]
  TestTime Adaptation (TTA) enables the model to adaptively estimate r signals in various unseen domains by online adapting to unlabeled target data without referring to any source data. We develop a synthetic signal-guided feature learning method by pseudo r signals as pseudo ground truths to guide a conditional generator in generating latent r features.
  arXiv  Detail & Related papers  (2024-07-18T09:22:40Z)
• Exploring Beyond Logits: Hierarchical Dynamic Labeling Based on Embeddings for Semi-Supervised Classification [49.09505771145326]
  We propose a Hierarchical Dynamic Labeling (HDL) algorithm that does not depend on model predictions and utilizes image embeddings to generate sample labels. Our approach has the potential to change the paradigm of pseudo-label generation in semi-supervised learning.
  arXiv  Detail & Related papers  (2024-04-26T06:00:27Z)
• Category-Adaptive Label Discovery and Noise Rejection for Multi-label Image Recognition with Partial Positive Labels [78.88007892742438]
  Training multi-label models with partial positive labels (MLR-PPL) attracts increasing attention. Previous works regard unknown labels as negative and adopt traditional MLR algorithms. We propose to explore semantic correlation among different images to facilitate the MLR-PPL task.
  arXiv  Detail & Related papers  (2022-11-15T02:11:20Z)
• Rethinking Pseudo Labels for Semi-Supervised Object Detection [84.697097472401]
  We introduce certainty-aware pseudo labels tailored for object detection. We dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem. Our approach improves supervised baselines by up to 10% AP using only 1-10% labeled data from COCO.
  arXiv  Detail & Related papers  (2021-06-01T01:32:03Z)
• On Signal-to-Noise Ratio Issues in Variational Inference for Deep Gaussian Processes [55.62520135103578]
  We show that the gradient estimates used in training Deep Gaussian Processes (DGPs) with importance-weighted variational inference are susceptible to signal-to-noise ratio (SNR) issues. We show that our fix can lead to consistent improvements in the predictive performance of DGP models.
  arXiv  Detail & Related papers  (2020-11-01T14:38:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.