Video-based Heart Rate Estimation with Angle-guided ROI Optimization and Graph Signal Denoising

Gan Pei; Junhao Ning; Boqiu Shen; Yan Zhu; Menghan Hu

cs.CVApr 13, 2026

Video-based Heart Rate Estimation with Angle-guided ROI Optimization and Graph Signal Denoising

Authors: Gan Pei, Junhao Ning, Boqiu Shen, Yan Zhu, Menghan Hu

Organizations: Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University · Shanghai Changzheng Hospital, Naval Military Medical University · Chongqing Key Laboratory of Precision Optics, Chongqing Institute of East China Normal University

Abstract

Remote photoplethysmography (rPPG) enables non-contact heart rate measurement from facial videos, but its performance is significantly degraded by facial motions such as speaking and head shaking. To address this issue, we propose two plug-and-play modules. The Angle-guided ROI Adaptive Optimization module quantifies ROI-Camera angles to refine motion-affected signals and capture global motion, while the Multi-region Joint Graph Signal Denoising module jointly models intra- and inter-regional ROI signals using graph signal processing to suppress motion artifacts. The modules are compatible with reflection model-based rPPG methods and validated on three public datasets. Results show that jointly use markedly reduces MAE, with an average decrease of 20.38% over the baseline, while ablation studies confirm the effectiveness of each module. The work demonstrates the potential of angle-guided optimization and graph-based denoising to enhance rPPG performance in motion scenarios.

Figures & tables

Figure 1: Challenges of reflection model-based rPPG methods for HR estimation and the proposed solutions.

Figure 2: Pipeline of HR measurement framework is shown, with variables consistent with those in Sec. 2 . Angle-guided ROI Adaptive Optimization module aims to detect global head motion based on angular features and to refine ROI signals, while Multi-Region Joint Graph Signal Denoising module purifies heart rate signals by jointly modeling and denoising ROI signals.

Figure 3: Global motion detection can effectively identifying head rotations and nods on the PURE dataset.

S-E	S-P	COHFACE		PURE		MMPD
S-E	S-P	MAE↓	MAPE↓	MAE↓	MAPE↓	MAE↓	MAPE↓
PBV & SROI	BP	7.61	11.83	6.54	8.15	20.40	22.35
PBV & AGROI	BP	5.82	6.17	5.72	6.24	19.87	21.73
PBV & AGROI	BGSD	5.68	8.29	4.52	6.13	18.94	21.59
POS & SROI	BP	5.18	7.18	5.88	6.33	16.16	18.06
POS & AGROI	BP	4.63	6.42	5.31	5.46	15.45	17.56

Table 1: Performance comparison of baseline rPPG methods with angle-guided ROI module (AGROI) and multi-region joint graph signal denoising module (GSD) on three public datasets. S-E: Signal Extraction; S-P: Signal Processing; SROI: Single ROI; BP: Bandpass; BGSD: Bandpass & GSD.

Heart Rate Estimation

Heart rate estimation recovers beats per minute from wearable, contact, or remote physiological signals.

See all 31 papers

MVRD-Bench: Multi-View Learning and Benchmarking for Dynamic Remote Photoplethysmography under Occlusion
Mar 24, 2026Zuxian He, Xu Cheng, Zhaodong Sun +4Remote Photoplethysmography Multi-View Learning
Nanjing University of Information Science and Technology · University of Oulu · Xi’an Jiaotong University +1
PhysNeXt: Next-Generation Dual-Branch Structured Attention Fusion Network for Remote Photoplethysmography Measurement
Mar 20, 2026Junzhe Cao, Bo Zhao, Zhiyi Niu +5Remote Photoplethysmography Heart Rate Estimation
Harbin Institute of Technology, Shenzhen · Great Bay University · Hefei University of Technology +1
CardiacMamba: Fair and Robust RGB-RF Fusion for Remote Heart Rate Estimation via State Space Modeling
Aug 16, 2026Bo Zhao, Zheng Wu, Yiping Xie +1Heart Rate Estimation Remote Photoplethysmography
Great Bay University

Mar 24, 2026J/K move · Enter open · S save

MVRD-Bench: Multi-View Learning and Benchmarking for Dynamic Remote Photoplethysmography under Occlusion

Zuxian He, Xu Cheng, Zhaodong Sun, Haoyu Chen+3

Nanjing University of Information Science and Technology · University of Oulu · Xi’an Jiaotong University+1

Remote Photoplethysmography Multi-View Learning

Open paper AskPDF arXiv

Remote photoplethysmography (rPPG) is a non-contact technique that estimates physiological signals by analyzing subtle skin color changes in facial videos. Existing rPPG methods often encounter performance degradation under facial motion and occlusion scenarios due to their reliance on static and single-view facial videos. Thus, this work focuses on tackling the motion-induced occlusion problem for rPPG measurement in unconstrained multi-view facial videos. Specifically, we introduce a Multi-View rPPG Dataset (MVRD), a high-quality benchmark dataset featuring synchronized facial videos from three viewpoints under stationary, speaking, and head movement scenarios to better match real-world conditions. We also propose MVRD-rPPG, a unified multi-view rPPG learning framework that fuses complementary visual cues to maintain robust facial skin coverage, especially under motion conditions. Our method integrates an Adaptive Temporal Optical Compensation (ATOC) module for motion artifact suppression, a Rhythm-Visual Dual-Stream Network to disentangle rhythmic and appearance-related features, and a Multi-View Correlation-Aware Attention (MVCA) for adaptive view-wise signal aggregation. Furthermore, we introduce a Correlation Frequency Adversarial (CFA) learning strategy, which jointly enforces temporal accuracy, spectral consistency, and perceptual realism in the predicted signals. Extensive experiments and ablation studies on the MVRD dataset demonstrate the superiority of our approach. In the MVRD movement scenario, MVRD-rPPG achieves an MAE of 0.90 and a Pearson correlation coefficient (R) of 0.99. The source code and dataset will be made available.

Abstract

Heart Rate Estimation

Explore similar work

MVRD-Bench: Multi-View Learning and Benchmarking for Dynamic Remote Photoplethysmography under Occlusion

PhysNeXt: Next-Generation Dual-Branch Structured Attention Fusion Network for Remote Photoplethysmography Measurement

CardiacMamba: Fair and Robust RGB-RF Fusion for Remote Heart Rate Estimation via State Space Modeling