Asphalt mixture CT image generation method based on generative adversarial network

The invention discloses an asphalt mixture CT image generation method based on a generative adversarial network, relates to the technical field of road engineering, and aims to solve the problem that the existing asphalt mixture CT image generation method does not consider aggregate particle spacing, aggregate particle area ratio and void ratio and cannot truly reflect the real structure distribution condition of an asphalt mixture. In order to solve the problem of low accuracy of the generated CT image of the asphalt mixture due to the fact that the CT image of the asphalt mixture is generated in the prior art, the method introduces mesoscopic indexes (aggregate particle spacing, aggregate particle area ratio and void ratio) of the asphalt mixture by modifying loss functions of a generator and a discriminator, improves the similarity between the generated image and a real image, and improves the accuracy of the CT image of the asphalt mixture. The method is beneficial to detail processing of the generated im