Spatial misregistration and cross-modal discrepancies often cause ghosting, structural blurring, and content imbalance in RGB-T fusion. Existing methods typically decouple appearance adaptation, geometric alignment, and information fusion, limiting dependency propagation across stages. We propose Source-Anchored Guidance via Frequency Equalization for Hierarchical RGB-T Alignment and Fusion (SAGE), a unified framework integrating frequency equalization, hierarchical alignment, and subband fusion. SAGE employs invertible joint encoding and source-specific low-frequency modulation to derive structural and gain guidance while preserving source information. Hierarchical frequency collaborative alignment estimates global affine geometry from low-frequency approximations and transfers geometric and contextual cues to high-frequency correlation reasoning for reliability-aware residual refinement. Guided subband fusion jointly aggregates the aligned frequency coefficients under propagated source and alignment guidance, coordinates complementary low- and high-frequency information, and reconstructs the fused image through the inverse wavelet transform. Extensive experiments on RGB-T datasets with real-world and synthetic misalignments demonstrate consistently competitive performance in alignment and fusion, validating the effectiveness of source-anchored guidance for weakly registered RGB-T images.
Figures & tables
Figure 1: Comparison between a conventional pipeline based on image translation and SAGE. (a) Image translation, alignment, and fusion are performed sequentially. (b) SAGE uses source-anchored frequency equalization to guide hierarchical alignment from low to high frequencies and subband fusion. Solid arrows denote feature and dependency flows, while dashed arrows denote guidance propagation.
Figure 2: Overview of SAGE. The source anchored frequency guidance mechanism consistently propagates structural and gain cues across frequency equalization, hierarchical alignment, and subband fusion. SAFE reduces low frequency discrepancy while preserving source high frequency details. HFCA combines low frequency affine alignment with reliability guided high frequency refinement. GSF adaptively fuses the aligned subbands and reconstructs the final image through inverse Haar wavelet transform.
Figure 3: Qualitative comparisons on DroneVehicle, MFNet, and RoadScene.
Method
DroneVehicle
MFNet
RoadScene
AG ↑
SCD ↑
SF ↑
HD95 ↓
ASSD ↓
AG ↑
SCD ↑
SF ↑
HD95 ↓
ASSD ↓
AG ↑
SCD ↑
SF ↑
HD95 ↓
ASSD ↓
SuperFusion
6.11
0.91
17.50
30.12
7.55
2.96
1.06
7.90
63.83
14.49
4.33
1.21
11.67
44.43
10.38
ReCoNet
5.20
1.48
13.60
30.53
7.71
3.15
1.53
9.51
69.72
17.71
3.65
1.27
9.02
45.72
11.57
MURF
2.34
0.89
5.72
44.95
12.06
3.02
1.36
10.47
30.47
6.77
3.49
1.27
9.79
39.36
8.43
UMF-CMGR
4.28
1.02
10.96
31.73
8.93
1.81
1.07
5.25
100.17
39.25
2.90
0.61
3.86
65.27
22.19
IMF
4.11
1.01
8.44
30.97
8.62
1.23
0.77
3.77
68.03
25.70
3.50
1.25
7.43
56.76
18.32
Table 1: Quantitative comparison with SOTA methods. The bold / underline indicates the best and runner-up.
Figure 4: Qualitative ablation results on MFNet.
Methods
AG ↑
SCD ↑
SF ↑
HD95 ↓
ASSD ↓
w/o SAFE
2.72
1.19
9.86
29.46
5.82
w/o LFA
3.09
1.36
7.97
35.40
7.09
w/o HCR
2.68
1.14
8.58
36.20
7.36
w/o GSF
2.76
1.35
8.11
35.08
6.85
SAGE
3.17
1.28
11.49
21.65
4.24
Table 2: Ablation results on MFNet. LFA, HCR, and GSF denote low-frequency affine alignment, high-frequency correlation refinement, and guided subband fusion, respectively.
Figure 5: Effects of guidance propagation to low-frequency alignment, high-frequency alignment, fusion, or all stages.
Figure 6: Comparison of collaboration strategies in (a) HF alignment gain and (b) post-alignment LL correlation.
Methods
Recall ↑
Precision ↑
mAP@ 0.5↑
SuperFusion
23.40
14.11
11.43
ReCoNet
24.59
13.28
10.31
MURF
27.51
11.17
10.69
UMF-CMGR
26.94
11.96
10.80
IMF
21.85
11.67
8.83
AU-Net
24.87
12.54
10.56
Table 3: Quantitative object detection results on DroneVehicle. The bold / underline indicates the best and runner-up.
Methods
FLOPs (G)
Parameters (M)
Time (s)
FPS
SuperFusion
16.36
1.96
0.03
38.69
ReCoNet
15.33
0.21
0.33
3.05
MURF
100.10
4.08
0.12
8.13
UMF-CMGR
131.38
14.44
0.09
10.69
IMF
123.30
15.70
0.06
17.07
AU-Net
14.04
2.27
0.02
60.93
Table 4: Model complexity and inference efficiency.