Domain Generalized RPPG Network: Disentangled Feature Learning with Domain Permutation and Domain Augmentation

Wei-Hao Chung, Cheng-Ju Hsieh, Sheng-Hung Liu, Chiou-Ting Hsu; Proceedings of the Asian Conference on Computer Vision (ACCV), 2022, pp. 807-823

Abstract


Remote photoplethysmography (rPPG) offers a contactless method for monitoring physiological signals from facial videos. Existing learning-based methods, although work effectively on intra-dataset scenarios, degrade severely on cross-dataset testing. In this paper, we address the cross-dataset testing as a domain generalization problem and propose a novel DG-rPPGNet to learn a domain generalized rPPG estimator. To this end, we develop a feature disentangled learning framework to disentangle rPPG, identity, and domain features from input facial videos. Next, we propose a domain permutation strategy to further constrain the disentangled rPPG features to be invariant to different domains. Finally, we design a novel adversarial domain augmentation strategy to enlarge the domain sphere of DG-rPPGNet. Our experimental results show that DG-rPPGNet outperforms other rPPG estimation methods in many cross-domain settings on UBFC-rPPG, PURE, COHFACE, and VIPL-HR datasets.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Chung_2022_ACCV, author = {Chung, Wei-Hao and Hsieh, Cheng-Ju and Liu, Sheng-Hung and Hsu, Chiou-Ting}, title = {Domain Generalized RPPG Network: Disentangled Feature Learning with Domain Permutation and Domain Augmentation}, booktitle = {Proceedings of the Asian Conference on Computer Vision (ACCV)}, month = {December}, year = {2022}, pages = {807-823} }