Research map / Video / Video segmentation and tracking
Remote Heart Rate Measurement From Highly Compressed Facial Videos: An End-to-End Deep Learning Solution With Video Enhancement
Zitong Yu, Wei Peng, Xiaobai Li, Xiaopeng Hong, Guoying Zhao
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add skin segmentation branch (multi-task) (ablation) | rPPGNet_base · OBF (original videos) | HR RMSE: 2.772 -> 2.587 | Improved |
| add partition constraint (ablation) | rPPGNet_base+Skin · OBF (original videos) | HR RMSE: 2.587 -> 2.087 | Improved |
| add skin-based attention (ablation) | rPPGNet_base+Skin · OBF (original videos) | HR RMSE: 2.587 -> 2.051 | Improved |
| combine partition constraint and attention (full model) (ablation) | rPPGNet_base+Skin · OBF (original videos) | HR RMSE: 2.587 -> 1.8 | Improved |
| full rPPGNet versus best traditional baseline POS | POS · OBF (original videos) | LF/HF RMSE: 0.679 -> 0.589 | Improved |
| use spatial-wise softmax instead of spatio-temporal softmax in attention (ablation) | rPPGNet attention · OBF (original videos) | HR | Improved |
| use negative Pearson loss instead of MSE loss (ablation) | rPPGNet · OBF (original videos) | HR | Improved |
| lower video bitrate (compression) | rPPGNet and traditional methods · OBF (compressed 250/500/1000 kb/s) | HR | Hurt |
| add STVEN enhancement before rPPGNet | rPPGNet · MAHNOB-HCI | HR RMSE: 7.82 -> 5.93 | Improved |
| add STVEN enhancement before rPPGNet | rPPGNet · MAHNOB-HCI | HR MAE: 5.51 -> 4.03 | Improved |
| add DnCNN enhancement instead of STVEN (ablation) | rPPGNet · OBF x264 compressed | HR | Hurt |
| joint training instead of separate training (ablation) | STVEN+rPPGNet · OBF x264 compressed | HR | Improved |
Closest papers by meaning
- PhysFormer: Facial Video-Based Physiological Measurement With Temporal Difference Transformer (CVPR 2022 · similarity 0.93)
- Facial Video-based Remote Physiological Measurement via Self-supervised Learning (TPAMI 2023 · similarity 0.93)
- PhysFormer++: Facial Video-Based Physiological Measurement with SlowFast Temporal Difference Transformer (IJCV 2023 · similarity 0.92)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.91)
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios (CVPR 2025 · similarity 0.90)
- FacePhys: State of the Heart Learning (NeurIPS 2026 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
