Research map / Video / Video segmentation and tracking
rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training
Tianyang Dai, Ming Chang, Yan Chen, Yang Hu
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 frequency consistency weight to simple SNR averaging (ablation) | signal-level branch · PURE ablation: signal-level branch | MAE: 0.82 -> 0.52 | Improved |
| add spectral correlation weight to simple SNR averaging (ablation) | signal-level branch · PURE ablation: signal-level branch | MAE: 0.82 -> 0.57 | Improved |
| add spectral correlation weight on top of frequency consistency weight (ablation) | signal-level branch · PURE ablation: signal-level branch | MAE: 0.52 -> 0.47 | Improved |
| add ranking-based filtering to WRS (ablation) | TAS · PURE ablation: TAS components | MAE: 0.71 -> 0.70 | No clear effect |
| add duration-aware sampling to WRS (ablation) | TAS · PURE ablation: TAS components | MAE: 0.71 -> 0.49 | Improved |
| combine filtering with duration-aware sampling (full TAS) (ablation) | TAS · PURE ablation: TAS components | MAE: 0.71 -> 0.47 | Improved |
| mix scene-level score into quality score (alpha 0.8 instead of 1.0) (ablation) | rPPG-VQA · PURE ablation: fusion weight alpha | MAE: 0.78 -> 0.47 | Improved |
| use only scene-level score (alpha 0.0 instead of 0.8) (ablation) | rPPG-VQA · PURE ablation: fusion weight alpha | MAE: 0.47 -> 6.91 | Hurt |
| use TAS instead of Top/Bottom K with rPPG-VQA score | Contrast-Phys · PURE test (train on curated in-the-wild data) | MAE: 1.36 -> 0.47 | Improved |
| use rPPG-VQA criterion instead of IPR under WRS | Contrast-Phys · PURE test (train on curated in-the-wild data) | MAE: 4.89 -> 0.71 | Improved |
| use rPPG-VQA criterion instead of SNR under Top/Bottom K | Contrast-Phys · PURE test (train on curated in-the-wild data) | MAE: 2.34 -> 1.36 | Improved |
| curated Celeb-DF subset added to CAS(ME)2 instead of full Celeb-DF | Contrast-Phys · PURE test (train on curated in-the-wild data) | MAE: 31.07 -> 0.47 | Improved |
Closest papers by meaning
- Learning Motion-Robust Remote Photoplethysmography through Arbitrary Resolution Videos (AAAI 2023 · similarity 0.92)
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios (CVPR 2025 · similarity 0.91)
- Synthetic Generation of Face Videos With Plethysmograph Physiology (CVPR 2022 · similarity 0.91)
- Contrast-Phys+: Unsupervised and Weakly-Supervised Video-Based Remote Physiological Measurement via Spatiotemporal Contrast (TPAMI 2024 · similarity 0.91)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.89)
- PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement (AAAI 2025 · 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.
