StreamPPG: Low-Latency rPPG Estimation via Consistent Privileged Learning

• URL: http://arxiv.org/abs/2606.23186v1
• Date: Mon, 22 Jun 2026 11:31:01 GMT
• Title: StreamPPG: Low-Latency rPPG Estimation via Consistent Privileged Learning
• Abstract summary: Remote photoplethysmography (rmography) estimates the blood volume pulse (BVP) signal from facial videos, enabling contact-free health monitoring.<n> Conventional clip-wise approaches, which use video clips as input, require capturing over one hundred frames before introducing inference.<n>We propose Stream, a unified architecture that enables low-latency frame-wise physiological signal estimation.
• Score: 24.385061454563836
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Remote photoplethysmography (rPPG) estimates the blood volume pulse (BVP) signal from facial videos, enabling contact-free health monitoring. Conventional clip-wise approaches, which use video clips as input, require capturing over one hundred frames before inference, thus introducing several seconds of delay and hindering real-time use. Meanwhile, frame-wise approaches struggle to capture long-range temporal and periodic features of physiological rhythms, and therefore lead to reduced estimation accuracy. To overcome these issues, we propose StreamPPG, a unified architecture that enables low-latency frame-wise physiological signal estimation while achieving competitive accuracy compared with clip-wise approaches. StreamPPG is trained under a consistent privileged learning (CPL) strategy, which leverages ground-truth rPPG signals as privileged information to enhance the model's representation capability. Extensive experiments demonstrate that StreamPPG achieves state-of-the-art accuracy across multiple datasets while maintaining real-time throughput on edge devices.

Related papers

• FCUS-rPPG: A Fast-Converging Unsupervised Framework for Remote Photoplethysmography via Gradient Oscillation Suppression [19.91628990903841]
  Photoplethysmography (rmography) enables non-contact extraction of blood volume pulse (BVP) signals using consumer-grade cameras.<n>FCUS-r is a fastconverging unsupervised r framework with strong generalization capability.<n>FCUS-r consistently achieves state-of-the-art evaluations in cross-dataset performance.
  arXiv  Detail & Related papers  (2026-06-02T02:33:27Z)
• Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs [66.15429821530503]
  Persistent Visual Memory is a lightweight learnable module designed to strengthen sustained, on-demand access to visual evidence.<n>Experiments on Qwen3-VL models demonstrate that PVM brings notable improvements with negligible parameter overhead.<n>In-depth analysis reveals that PVM shows improved robustness in longer generations and accelerates internal prediction convergence.
  arXiv  Detail & Related papers  (2026-05-01T17:54:37Z)
• Towards Athlete Fatigue Assessment from Association Football Videos [53.20057980542362]
  This paper builds on state-of-theart Game State Reconstruction methods to extract player trajectories in pitch coordinates.<n>We then construct acceleration--speed profiles from these signals and analyze their behavior as fatigue-related performance indicators.<n>Our results indicate that monocular broadcast videos can recover kinematic patterns that are compatible with A-S-temporal while also revealing sensitivity to trajectory noise, calibration errors, and temporal discontinuities inherent to broadcast footage.
  arXiv  Detail & Related papers  (2026-04-07T09:36:28Z)
• Video Depth Propagation [54.523028170425256]
  Existing methods rely on simple frame-by-frame monocular models, leading to temporal inconsistencies and inaccuracies.<n>We propose VeloDepth, which effectively leverages an online video pipeline and performs deep feature propagation.<n>Our design structurally enforces temporal consistency, resulting in stable depth predictions across consecutive frames with improved efficiency.
  arXiv  Detail & Related papers  (2025-12-11T15:08:37Z)
• Reperio-rPPG: Relational Temporal Graph Neural Networks for Periodicity Learning in Remote Physiological Measurement [0.0]
  Remote photoplethys (rmography) is an emerging physiological sensing technique that leverages subtle color variations in facial videos to estimate vital signs such as heart rate and respiratory rate.<n>This non-invasive technique has gained traction across diverse domains, but its ability to capture fine-grained temporal dynamics under real-world conditions has been underexplored.<n>We propose Graph Reperio-r, a novel framework that strategically integrates a Transformer to effectively capture the periodic structure.
  arXiv  Detail & Related papers  (2025-11-08T09:41:34Z)
• DiTVR: Zero-Shot Diffusion Transformer for Video Restoration [48.97196894658511]
  DiTVR is a zero shot video restoration framework that couples a diffusion transformer with trajectory aware attention and a flow consistent sampler.<n>Our attention mechanism aligns tokens along optical flow trajectories, with particular emphasis on vital layers that exhibit the highest sensitivity to temporal dynamics.<n>The flow guided sampler injects data consistency only into low-frequency bands, preserving high frequency priors while accelerating cache.
  arXiv  Detail & Related papers  (2025-08-11T09:54:45Z)
• Towards Accurate Heart Rate Measurement from Ultra-Short Video Clips via Periodicity-Guided rPPG Estimation and Signal Reconstruction [8.153034573979857]
  We aim to accurately measure HR from ultra-short 2-second video clips by addressing two key challenges.<n>First, to overcome the limited number of heartbeat cycles in ultra-short video clips, we propose an effective periodicity-guided r estimation method.<n>Second, to mitigate inaccuracies due to spectral leakage, we propose a generator to reconstruct longer r signals.
  arXiv  Detail & Related papers  (2025-06-27T10:05:00Z)
• Periodic-MAE: Periodic Video Masked Autoencoder for rPPG Estimation [6.32655874508904]
  We propose a method that learns a general representation of periodic signals from unlabeled facial videos by capturing subtle changes in skin tone over time.<n>We evaluate the proposed method on the PURE, U-BFCr, MMPD, and V-BFC4V datasets.<n>Our results demonstrate significant performance improvements, particularly in challenging cross-dataset evaluations.
  arXiv  Detail & Related papers  (2025-06-27T02:18:10Z)
• Recovering Pulse Waves from Video Using Deep Unrolling and Deep Equilibrium Models [45.94962431110573]
  Camera-based monitoring of vital signs, also known as imaging photoplethysmography (i), has seen applications in driver-monitoring, affective computing, and more.<n>We introduce methods that combine signal processing and deep learning methods in an inverse problem.
  arXiv  Detail & Related papers  (2025-03-21T16:11:21Z)
• No-frills Temporal Video Grounding: Multi-Scale Neighboring Attention and Zoom-in Boundary Detection [52.03562682785128]
  Temporal video grounding aims to retrieve the time interval of a language query from an untrimmed video. A significant challenge in TVG is the low "Semantic Noise Ratio (SNR)", which results in worse performance with lower SNR. We propose a no-frills TVG model that consists of two core modules, namely multi-scale neighboring attention and zoom-in boundary detection.
  arXiv  Detail & Related papers  (2023-07-20T04:12:10Z)
• WPPG Net: A Non-contact Video Based Heart Rate Extraction Network Framework with Compatible Training Capability [21.33542693986985]
  Our facial skin presents subtle color change known as remote Photoplethys (r) signal, from which we could extract the heart rate of the subject. Recently many deep learning methods and related datasets on r signal extraction are proposed. However, because of the time consumption blood flowing through our body and other factors, label waves such as BVP signals have uncertain delays with real r signals in some datasets. In this paper, by analyzing the common characteristics on rhythm and periodicity of r signals and label waves, we propose a whole set of training methodology which wraps these networks so that they could remain efficient when be trained at
  arXiv  Detail & Related papers  (2022-07-04T19:52:30Z)
• Intrinsic Temporal Regularization for High-resolution Human Video Synthesis [59.54483950973432]
  temporal consistency is crucial for extending image processing pipelines to the video domain. We propose an effective intrinsic temporal regularization scheme, where an intrinsic confidence map is estimated via the frame generator to regulate motion estimation. We apply our intrinsic temporal regulation to single-image generator, leading to a powerful " INTERnet" capable of generating $512times512$ resolution human action videos.
  arXiv  Detail & Related papers  (2020-12-11T05:29:45Z)

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.