Remote photoplethysmography (rPPG) enables non-contact heart rate (HR) monitoring from facial videos, but RGB-only methods are vulnerable to illumination changes, motion artifacts, and skin-tone-dependent optical reflectance. We propose CardiacMamba, a fair and robust RGB-RF fusion framework that integrates optical facial cues and radio-frequency cardiac motion cues through state space modeling. CardiacMamba introduces a Temporal Difference Mamba Module (TDMM) to enhance subtle RF temporal variations, a bidirectional SSM-based interaction mechanism to align heterogeneous RGB-RF dynamics, and a Channel-wise Fast Fourier Transform (CFFT) module for channel-domain spectral refinement. On the EquiPleth dataset, CardiacMamba achieves state-of-the-art performance with 0.96 bpm MAE, 3.06 bpm RMSE, and 0.97 Pearson correlation, while reducing the observed light-dark skin-tone MAE gap to 0.26 bpm and maintaining robustness under RGB degradation and RF-missing conditions
Figures & tables
Figure 1: The overall architecture of CardiacMamba. It consists of three stages: Dual-level Feature Extraction and Alignment, Bidirectional Feature Interaction, and Bidirectional Feature Fusion.
Figure 2: Channel-wise Fast Fourier Transform (CFFT) for refining RGB and RF representations through channel-domain spectral interaction.
Table 1: Comparison of different methods on the EquiPleth dataset. The best results are marked in bold .
Method
Train
Test
MAE
RMSE
Base
RGB&RF
RGB
21.7
25.7
Base
RGB&RF
RF
21.4
24.3
Base
RGB&RF
RGB&RF
20.3
24.8
Vilesov et al. [ 7 ]
RGB&RF
RGB
6.82
13.32
Vilesov et al. [ 7 ]
RGB&RF
RF
7.25
9.62
Vilesov et al. [ 7 ]
RGB&RF
RGB&RF
1.12
3.42
Table 2: Testing under missing-modality conditions.
Vim
CFFT
SSM
RFAM
TDMM
MAE
RMSE
ρ
×
✓
✓
✓
✓
1.7
4.9
0.91
✓
×
✓
✓
✓
4.92
6.33
0.77
✓
✓
×
✓
✓
1.86
5.51
0.89
✓
✓
✓
×
✓
1.85
5.31
0.9
✓
✓
✓
✓
×
3.82
8.06
0.81
✓
✓
✓
✓
✓
0.96
3.06
0.97
Table 3: Ablation on different modules, including ‘Vim’ (short for Vision Mamba), ‘CFFT’ (short for Channel-wise Fast Fourier Transform), ‘RFAM’ (short for RF Alignment Module), and ‘TDMM’ (short for Temporal Difference Mamba Module).
Model
Condition
MAE
RMSE
ρ
Ours (RGB-Only)
Normal
1.20
4.23
0.95
+ Gaussian Noise
8.54
15.12
0.41
Ours (Full model)
Normal
0.96
3.06
0.97
+ Gaussian Noise
2.15
5.80
0.88
Table 4: Ablation study on model robustness under simulated RGB signal degradation. We added Gaussian noise to the RGB input to test performance. Best results under noisy conditions are in bold .
Figure 4: Visual representations of features (from left to right): human face, feature heat map, radar spectrum diagram, and its feature heat map.
Figure 5: Bland-Altman plots comparing estimated and ground-truth heart rates.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Method
Input
Δ MAE
Δ RMSE
Δρ
ICA [ 18 ]
RGB
4.42
3.15
-0.36
CHROM [ 1 ]
RGB
4.97
4.17
-0.38
BCG [ 19 ]
RGB
0.99
1.25
0.05
PhysNet [ 2 ]
RGB
2.22
4.05
-0.25
FFT-based RF [ 3 ]
RF
1.32
2.06
0.32
Vilesov et al. [ 7 ]
RGB&RF
0.67
1.44
-0.10
Appendix
Table 5: Comparison of the Fairness of various methods on the RGB and RF fusion task, with the differences in performance ( Δ ) between light and dark skin tones in terms of MAE, RMSE, and correlation coefficient ( ρ ).