Abstract: The current deep learning SAR image simulation methods generally do not consider the feature differences of different geomorphic categories in SAR images, resulting in the distortion of geomorphic differentiation in simulated images. In view of this situation, this paper proposes a visible-to-SAR image translation algorithm guided by geomorphic category information. The main innovations of the algorithm are as follows: 1. Design a topographic category extraction branch and use attention mechanism to collect topographic category information from multiple dimensions to guide SAR image simulation; 2. Design image content extraction branches and use contrast learning to enhance the feature extraction capability of the network for the common content information of visible light and SAR images; 3. The image generation module is designed to convert content information into SAR images under the guidance of geomorphic category information, so that the generated SAR images have features corresponding to geomorphic category, and the path regularization is used to subdivide the complete translation process from visible light to SAR images to reduce the difficulty of implementation. A pair dataset of visible and SAR images with different landforms is established. After experimental comparison of 6 evaluation indexes, the proposed algorithm has better performance than other representative algorithms, and the structural similarity is improved by at least 9.24%. At the same time, the simulated SAR image shows a higher degree of realism in the visual effect, and can effectively retain the features of landform categories.

Key words: SAR, Deep Learning, Multi-Category Terrain, Attention Mechanism, Contrastive Learning, Path Regularization