**6. Discussion**

In order to further analyze the performance of the SMD-Net under the small training samples, in the 10 groups of interferogram patches in Section 4.1, 200 interferogram patches were selected starting from the first interferogram patch in each group at an interval of 10 interferograms as new training sets. Then, the SMD-Net was retrained with the training sets. The indicators of the testing results on the simulated data are listed in Table 4. As can be seen in Table 4, the MSE of the proposed method was 9.3% higher, but the MSSIM of the proposed method was equal to that of PFNet and its T was 85.5% faster. Therefore, it can be seen that the performance of the SMD-Net trained with 200 training samples was comparable to the PFNet trained with 2250 training samples. Unlike the PFNet, the performance of the SMD-Net was not constrained by the requirement of the data volume.

**Table 4.** The metrics of the PFNet trained with 2250 samples and the SMD-Net trained with 200 samples on the simulated data. MSSIM is the core accuracy index. T is the speed index.


Like the simulated data, we processed the measured data utilizing the SMD-Net trained with 200 training samples to analyze the filtering performance of the proposed method. The filtering result of area A (Figure 9a) is shown in Figure 12b, and we can see intuitively from the black rectangles in Figure 12a,b that the phase detail features of the result obtained by our method were better preserved. Next, a flat and low-coherence area B (Figure 9b) was processed to prove the generalization of the proposed method. The black rectangles in Figure 12c,d also showed that the proposed method had a stronger phase edge texture preservation capability.

Furthermore, the quantitative indicators of the two areas were calculated and are listed in Tables 5 and 6. Tables 5 and 6, compared with the PFNet, it could be observed that the NORs of the proposed method were higher in both areas, but their metric Qs were higher. This indicates that the PFNet caused the serious loss of phase fringe detail information due to over filtering and its phase detail feature preservation capability was inferior to the proposed method. In addition, we could calculate that the metric Qs of the results obtained by processing area A and area B with the proposed method were 5.6% and 17.1% higher than that of the PFNet, respectively. To sum up, it can be seen that the filtering performance of the SMD-NET trained with 200 training samples outperformed that of the PFNet trained with 2250 training samples.

**Figure 12.** The filtered results obtained by processing area A and area B: (**a**) Filtered result of area A utilizing the PFNet trained with 2250 training samples; (**b**) the filtered result of area A utilizing the proposed method trained with 200 training samples; (**c**) the filtered result of area B utilizing the PFNet trained with 2250 training samples; (**d**) the filtered result of area B utilizing the proposed method trained with 200 training samples.

**Table 5.** The metrics of the PFNet trained with 2250 samples and the SMD-Net trained with 200 samples on area A. Metric Q is the core accuracy index. T is the speed index.


**Table 6.** The metrics of the PFNet trained with 2250 samples and the SMD-Net trained with 200 samples on area B. Metric Q is the core accuracy index. T is the speed index.

