AI Paper Atlas

Research map / Video / Video segmentation and tracking

Synthetic Generation of Face Videos With Plethysmograph Physiology

Zhen Wang, Yunhao Ba, Pradyumna Chari, Oyku Deniz Bozkurt, Gianna Brown, Parth Patwa, Niranjan Vaddi, Laleh Jalilian, Achuta Kadambi

CVPR 2022 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 39 citations (OpenAlex)

Check 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 changedWhereMeasuredEffect
Add synthetic training data to real-data training (ablation)PhysNet · UCLA-rPPG overallMAE: 1.06 -> 0.71Improved
Add synthetic training data to real-data training (ablation)PhysNet · UCLA-rPPG F5-6MAE: 2.61 -> 1.55Improved
Add synthetic training data to real-data training (ablation)PRN · UCLA-rPPG overallMAE: 1.43 -> 1.15Improved
Use synthetic data only instead of real data (ablation)PhysNet · UCLA-rPPG overallMAE: 1.06 -> 2.06Hurt
Use synthetic data only instead of real data (ablation)PRN · UCLA-rPPG overallMAE: 1.43 -> 2.87Hurt
Use synthetic data only rather than real training data (ablation)PhysNet · UBFC-rPPGMAE: 1.42 -> 0.84Improved
Use synthetic data only rather than real training data (ablation)PRN · UBFC-rPPGMAE: 2.36 -> 1.09Improved
Pre-train on multiple synthetic skin-tone groups instead of one group (ablation)PhysNet · UCLA-rPPG, especially dark skin tonesMAEImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy