Activity counts measure attention, not model quality. Missing counts are unknown. Publication status follows the linked source; a listed venue alone does not confirm peer review.
Domain-generalization add-on for end-to-end rPPG networks. Two modules: a Temporal Refinement Module (TRM) and Prototype-based Cross-Temporal Optimal Transport (PCOT), plus source-consistency and identity-preservation regularizers. Authors derive a generalization bound under conditional OT.
- Form factor
- camera_rppg
- Year
- 2026
- Title
FLOW: Feature-Level Optimal Warping for Generalized Remote Physiological Measurement
- Authors
Bo Zhao, Junzhe Cao, Dan Guo, Dongmin Huang, Wenjin Wang, Tao Tan, Yue Sun, Zitong Yu
arXiv:2609.38913v1 (30 Sep 2026); HTML licence line CC BY 4.0; no code URL in the preprint
- Type
- Task model
- Modalities
- Not reported
- Form factor
- Camera rPPG
- Parameters
- Not reported
- Architecture
- Not reported
- Venue
- arXiv preprint
- Year
- 2026
- DOI
- Not reported
- Code
- Not reported
- Weights
- Not reported
- Caveats
- Not reported
- Datasets
- Not reported
- Added
- Not reported
- Updated
- Oct 26, 2026
Abstract
Remote photoplethysmography (rPPG) enables non-contact physiological measurement but remains vulnerable to domain shifts from illumination, motion, and sensors. We propose FLOW (Feature-Level Optimal Warping), an optimal transport–driven framework for domain-generalized rPPG. FLOW integrates a Temporal Refinement Module (TRM) to stabilize temporal dynamics and a Prototype-based Cross-Temporal Optimal Transport (PCOT) module to achieve domain-invariant alignment via learnable prototypes.Beyond feature alignment, FLOW employs soft cross-temporal correspondence modeling that aligns temporal features in a flexible manner, allowing the model to respect and preserve the intrinsic rhythmic patterns of physiological signals. Moreover, the lightweight design of our modules allows seamless integration into existing end-to-end rPPG architectures without additional preprocessing. Two regularization terms further enforce source consistency and identity preservation. Theoretically, we derive a generalization bound under conditional optimal transport. Extensive experiments across four rPPG benchmarks show that FLOW achieves state-of-the-art cross-domain performance with lightweight design and strong physiological fidelity.
Verbatim fromarXiv· arXiv metadata (abstracts are released under CC0)
How it works
- Approach
- rppg · model · domain generalization · optimal transport · plug in module
Datasets
Papers· 1
Cite
APA
Zhao, B., Cao, J., Guo, D., Huang, D., Wang, W., Tan, T., Sun, Y., & Yu, Z. (2026). FLOW: Feature-Level Optimal Warping for Generalized Remote Physiological Measurement. arXiv preprint. https://arxiv.org/abs/2609.38913
BibTeX
@misc{zhao2026flow,
title = {{FLOW: Feature-Level Optimal Warping for Generalized Remote Physiological Measurement}},
author = {Zhao, Bo and Cao, Junzhe and Guo, Dan and Huang, Dongmin and Wang, Wenjin and Tan, Tao and Sun, Yue and Yu, Zitong},
year = {2026},
howpublished = {arXiv preprint},
eprint = {2609.38913},
archivePrefix = {arXiv}
}Built from the hub record. Check it against the publisher before submitting.
History
Record updated