The invention provides a high-precision point cloud registration method for three-dimensional laser scanning. The method comprises steps of providing strategy of two steps from preposed coarse registration to iterative fine registration; carrying out curvature-based feature extraction on scattered point clouds which are obtained through three-dimensional laser scanning and have different visual angles to obtain feature points; and calculating coordinate transformation parameters of the matched feature point pairs to obtain a preposed coarse registration result, eliminating wrong homonymous points by using a distance constraint condition for the condition that the two-point cloud data is not in a subset relationship, and then performing iterative fine registration to obtain a final registration result. Feature point extraction is rapid and accurate, feature point matching accuracy is high, speed is high, coarse registration provides a good initial position for fine registration, after iterative fine registration is iterated to a certain number of times, an accurate result can reach very high precision, registration precision can reach the millimeter level, the method can be used forcomplex point cloud data, and engineering application requirements are met. The point cloud registration speed and precision are greatly improved, and the registration method is wide in application range.