Array Interferometric Synthetic Aperture Radar (ArrayInSAR) point cloud is a point cloud obtained by three-dimensional imaging of two-dimensional Synthetic Aperture Radar (SAR) images using array interferometric synthetic aperture radar technology, which can eliminate the phenomenon of layover in two-dimensional images and provide new data support for intelligent mapping. However, due to the influence of system thermal noise, baseline error and environment interference, there are noise points in the ArrayInSAR point cloud with uneven distribution and large elevation error, which bring a lot of gross errors to the 3D terrain results. To solve the problem that discrete points in ArrayInSAR point cloud data seriously affect the quality of three-dimensional data, this paper proposes an ArrayInSAR point cloud outlier noise removal method based on hybrid filtering. According to the distribution pattern of noise points, the outlier noise is divided into discrete outlier noise points and clusters of outlier noise. Firstly, the adaptive segmentation of point cloud dispersion coefficient within the k-neighborhood is used to remove discrete outlier noise points, and then the adaptive threshold segmentation algorithm based on the number of in-class points after K-means clustering is used to remove the cluster outlier noise of ArrayInSAR point cloud data. In order to verify the effectiveness, the proposed method is compared with other classical outlier noise removal methods. The experimental results show that the method proposed in this paper can effectively remove outlier noise in ArrayInSAR point cloud data and improve the quality of ArrayInSAR point clouds.

Polarimetric synthetic aperture radar (PolSAR) image classification requires the joint use of polarimetric scattering information and spatial context. However, aggregating or propagating information across locations with different scattering characteristics may mix features from dissimilar regions, and recurrent state propagation in Mamba can extend this influence along scan paths. Class-agnostic regions generated by the Segment Anything Model (SAM) from Pauli pseudo-RGB images may also span multiple land-cover classes, which may reduce the reliability of direct regional consistency constraints. This study proposes SSHMamba, a SAM-assisted scattering-guided hybrid selective Mamba network. It constructs a seven-channel scattering prior from the Pauli components, span, and H/A/α parameters. The local branch combines center-outward spiral rearrangement, one-dimensional convolution, and neighborhood weighting based on spatial distance and scattering similarity. In the long-range branch, the scattering prior conditions the state-space parameters, while scattering similarity and a learnable gate regulate the contribution of preceding states. Multidirectional outputs are aggregated using pixel-wise direction weights, and local and long-range features are fused using scattering-prior-driven channel-wise coefficients. During training, SAM candidate regions are screened using scattering homogeneity, prediction reliability, and region area before a soft regional consistency constraint is applied; SAM is not used during inference. Across three independent training runs under the same fixed data split, SSHMamba achieves 99.12 ± 0.04% OA, 99.13 ± 0.04% AA, and 0.9904 ± 0.0005 Kappa on Flevoland, and 99.42 ± 0.02% OA, 97.52 ± 0.03% AA, and 0.9909 ± 0.0004 Kappa on San Francisco. In the fixed reference runs, ECP-Mamba yields a slightly higher OA on Flevoland (99.30% versus 99.16%), whereas SSHMamba yields a higher OA on San Francisco (99.44% versus 99.20%). On Flevoland, removing the complete scattering-guided selective state propagation mechanism reduces OA from 99.16% to 96.48%. The SAM ablation shows that direct consistency over raw SAM regions yields 97.12% OA, candidate-region reliability screening increases it to 98.72%, and the full reliability-controlled SAM-assisted strategy reaches 99.16%. On the DLR E-SAR Oberpfaffenhofen dataset, SSHMamba achieves 99.29 ± 0.07% OA, 99.15 ± 0.04% AA, and 0.9889 ± 0.0006 Kappa across three runs, providing additional cross-sensor and cross-scene evidence.