RRGA-Net: Robust Point Cloud Registration Based on Graph Convolutional Attention.

The problem of registering point clouds in scenarios with low overlap is explored in this study. Previous methodologies depended on having a sufficient number of repeatable keypoints to extract correspondences, making them less effective in partially overlapping environments. In this paper, a novel learning network is proposed to optimize correspondences in sparse keypoints. Firstly, a multi-layer channel sampling mechanism is suggested to enhance the information in point clouds, and keypoints were filtered and fused at multi-layer resolutions to form patches through feature weight filtering. Moreover, a template matching module is devised, comprising a self-attention mapping convolutional neural network and a cross-attention network. This module aims to match contextual features and refine the correspondence in overlapping areas of patches, ultimately enhancing correspondence accuracy. Experimental results demonstrate the robustness of our model across various datasets, including ModelNet40, 3DMatch, 3DLoMatch, and KITTI. Notably, our method excels in low-overlap scenarios, showcasing superior performance.

Isothermal Experiments on Steam Oxidation of Zr-Sn-Nb Alloy at 1050 °C: Kinetics and Process.

The isothermal steam oxidation behavior of the Zr-Sn-Nb alloy at 1050 °C was studied. In this study, the oxidation weight gain of Zr-Sn-Nb samples with oxidation durations ranging from 100 s to 5000 s was calculated. The oxidation kinetic properties of the Zr-Sn-Nb alloy were obtained. The macroscopic morphology of the alloy was directly observed and compared. The microscopic surface morphology, cross-section morphology, and element content of the Zr-Sn-Nb alloy were analyzed using scanning electron microscopy (SEM), transmission electron microscopy (TEM), X-ray diffraction (XRD), and energy disperse spectroscopy (EDS). According to the results, the cross-sectional structure of the Zr-Sn-Nb alloy consisted of ZrO2, α-Zr(O), and prior-ß. During the oxidation process, its weight gain versus oxidation time curve followed a parabolic law. The thickness of the oxide layer increases. Micropores and cracks gradually appear on the oxide film. Similarly, the thicknesses of ZrO2 and α-Zr versus oxidation time were in accordance with the parabolic law.