Research map / 3D vision / Gaussian splatting
RhythmGuassian: Repurposing Generalizable Gaussian Model For Remote Physiological Measurement
Hao Lu, Yuting Zhang, Jiaqi Tang, Bowen Fu, Wenhang Ge, Wei Wei, Kaishun Wu, Yingcong Chen
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 explicit motion modeling (EMM) (ablation) | RhythmGaussian · VIPL-HR intra-dataset | HR MAE: 4.72 -> 4.22 | Improved |
| add explicit chroma modeling (ECM) (ablation) | RhythmGaussian · VIPL-HR intra-dataset | HR MAE: 4.64 -> 4.22 | Improved |
| add EMM (ablation) | RhythmGaussian · VIPL-HR intra-dataset | HR r: 0.84 -> 0.92 | Improved |
| add ECM (ablation) | RhythmGaussian · VIPL-HR intra-dataset | HR r: 0.86 -> 0.92 | Improved |
| add EMM (ablation) | RhythmGaussian · VIPL-HR intra-dataset | HR RMSE: 7.74 -> 7.12 | Improved |
| add ECM (ablation) | RhythmGaussian · VIPL-HR intra-dataset | HR RMSE: 7.81 -> 7.12 | Improved |
| add Gaussian modeling modules (EMM+ECM+virtual camera) to baseline | Baseline STMap network · VIPL-HR intra-dataset | HR MAE: 5.21 -> 4.22 | Improved |
| train on 9 additional rPPG datasets (Ours Pro) | RhythmGaussian · VIPL-HR | HR MAE: 7.05 -> 6.84 | Improved |
| train on 9 additional rPPG datasets (Ours Pro) | RhythmGaussian · V4V | HR MAE: 9.06 -> 8.62 | Improved |
| pretrain on 10 rPPG datasets instead of VIPL only | RhythmGaussian self-supervised · VIPL-HR linear probe | HR MAE: 7.24 -> 6.43 | Improved |
| use Gaussian self-supervised pretraining instead of rPPG-MAE | RhythmGaussian · VIPL-HR linear probe | HR MAE: 7.83 -> 7.24 | Improved |
| use RhythmGaussian instead of NEST | RhythmGaussian · UBFC cross-dataset | HR MAE: 4.7471 -> 4.2704 | Improved |
Closest papers by meaning
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios (CVPR 2025 · similarity 0.91)
- Learning Motion-Robust Remote Photoplethysmography through Arbitrary Resolution Videos (AAAI 2023 · similarity 0.91)
- rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training (CVPR 2026 · similarity 0.90)
- PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement (AAAI 2025 · similarity 0.90)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.90)
- Tricam-rPPG: A Multimodal Multispectral Dataset for remote Photoplethysmography (ECCV 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.
