AI Paper Atlas

Research map / Video / Video segmentation and tracking

Augmentation of rPPG Benchmark Datasets: Learning to Remove and Embed rPPG Signals via Double Cycle Consistent Learning from Unpaired Facial Videos

Cheng-Ju Hsieh, Wei-Hao Chung, Chiou-Ting Hsu

ECCV 2022 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 21 citations (OpenAlex)

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 changedWhereMeasuredEffect
add double-cycle loss and rPPG loss on Embedding-Net (ablation)RErPPG-Net · UBFC-rPPG ablationMAE: 44.79 -> 4.14Improved
add double-cycle loss and rPPG loss on Embedding-Net (ablation)RErPPG-Net · UBFC-rPPG ablationPSNR: 5.11 -> 49.72Improved
add double-cycle and rPPG-removal losses on Removal-Net (ablation)RErPPG-Net · UBFC-rPPG ablationMAE: 4.14 -> 2.30Improved
add multi-layer perceptual loss Lp (ablation)RErPPG-Net · UBFC-rPPG ablationMAE: 2.30 -> 0.71Improved
use double-cycle instead of single-cycle consistency (ablation)RErPPG-Net · UBFC-rPPGMAE: 2.38 -> 0.71Improved
train estimator on original plus augmented videosOurs estimator · UBFC-rPPGMAE: 0.66 -> 0.41Improved
train rPPGNet on original plus augmented videosrPPGNet · UBFC-rPPGMAE: 0.72 -> 0.56Improved
train on original plus augmented videos (30/12 split of [13])Ours estimator · UBFC-rPPG (30/12 split of [13])MAE: 0.64 -> 0.75Hurt
train estimator on original plus augmented videosOurs estimator · PUREMAE: 0.69 -> 0.38Improved
fine-tune on augmented UBFC videos, test on PUREOurs estimator · Cross-dataset test on PUREMAE: 14.18 -> 4.36Improved
fine-tune on augmented PURE videos, test on UBFCOurs estimator · Cross-dataset test on UBFC-rPPGMAE: 3.78 -> 2.23Improved
fine-tune on Aug-rPPG, test on VIPL-HROurs estimator · Cross-dataset test on VIPL-HRMAE: 28.94 -> 25.40Improved

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