Research map / Video / Video segmentation and tracking
SHINE-PPG: Non-Lambertian Intrinsic Decomposition for Illumination-Robust rPPG
Shih-Yu Yang, Yen-Chun Chou, Pei-Kai Huang, Chiou-Ting Hsu
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 |
|---|---|---|---|
| non-Lambertian decomposition (SHINE-PPG) vs Retinex-based Chen et al. | rPPG · MR-NIRP Car (intra-domain) | MAE (bpm): 2.16 -> 1.68 | Improved |
| SHINE-PPG vs best baseline on COHFACE | rPPG · COHFACE (intra-domain) | MAE (bpm): 1.17 -> 1.47 | No clear effect |
| SHINE-PPG vs prior methods in cross-domain dynamic lighting | rPPG · UBFC->Car | MAE (bpm): 9.80 -> 7.64 | Improved |
| SHINE-PPG vs Chen et al. correlation | rPPG · PURE->Car | Pearson R: 0.29 -> 0.74 | Improved |
| SHINE-PPG under driving illumination | rPPG · MR-NIRP Driving (trained on Garage) | MAE (bpm): 8.18 -> 6.80 | Improved |
| add reconstruction loss alone without constraints (ablation) | SHINE-PPG · PURE->Car (loss ablation) | Pearson R: 0.32 -> 0.19 | Hurt |
| add reflectance consistency and frequency constraints (ablation) | SHINE-PPG · PURE->Car (loss ablation) | Pearson R: 0.19 -> 0.48 | Improved |
| add specular loss (ablation) | SHINE-PPG · PURE->Car (loss ablation) | MAE (bpm): 4.17 -> 3.76 | Improved |
| add Color Jitter on decomposed illumination (ablation) | SHINE-PPG · PURE->Car (illumination enhancement) | MAE (bpm): 3.76 -> 3.56 | No clear effect |
| add Noise Injection on decomposed illumination (ablation) | SHINE-PPG · PURE->Car (illumination enhancement) | MAE (bpm): 3.76 -> 3.73 | No clear effect |
| add standard AdaIN illumination transfer (ablation) | SHINE-PPG · PURE->Car (illumination enhancement) | Pearson R: 0.57 -> 0.61 | No clear effect |
| add adversarial learnable AdaIN illumination enhancement (ablation) | SHINE-PPG · PURE->Car (illumination enhancement) | Pearson R: 0.57 -> 0.74 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PhysFormer — PhysFormer: Facial Video-Based Physiological Measurement With Temporal Difference Transformer (CVPR 2022) · better on 6 of 6 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- 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 0.90)
- PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement (AAAI 2025 · similarity 0.89)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.88)
- PaPaGei: Open Foundation Models for Optical Physiological Signals (ICLR 2025 · similarity 0.87)
- FacePhys: State of the Heart Learning (NeurIPS 2026 · similarity 0.87)
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.
