Point cloud denoising method based on generative adversarial network and self-attention mechanism

The invention relates to a point cloud denoising method based on a generative adversarial network and a self-attention mechanism, and belongs to the technical field of 3D point cloud denoising and the field of deep learning. The method comprises the following steps: constructing a point cloud to-be-denoised data set with noise, constructing a self-attention generator module, constructing a discriminator module, carrying out adversarial training on a generator and a discriminator until the generator and the discriminator reach Nash equilibrium, and finally obtaining a trained generator; and inputting the noise point cloud into the trained generator to obtain a denoised point cloud. According to the method, the generative adversarial network and the attention mechanism are combined, global and local features of the point cloud are further fused, more original point cloud details are reserved, the denoising effect is improved, and finer high-quality point cloud data are obtained. 本发明涉及一种基于生成对抗网络及自注意力机制的点云去噪方法，属于