eduzhai > Applied Sciences > Engineering >

Research on Image Generation and Style Transfer Algorithm Based on Deep Learning

  • Peter
  • (0) Download
  • 20210308
  • Save

... pages left unread,continue reading

Document pages: 12 pages

Abstract: Aimingat the current process of artistic creation and animation creation, there are alot of repeated manual operations in the process of conversion from sketch to the stylized image. This paper presented a solution based on a deeplearning framework to realize image generation and style transfer. The methodfirst used the conditional generation to resist the network, optimizes the lossfunction of the training mapping relationship, and generated the actual imagefrom the input sketch. Then, by defining and optimizing the perceptual lossfunction of the style transfer model, the style features are extracted from theimage, thereby forming the actual The conversion between images and stylizedart images. Experiments show that this method can greatly reduce the work ofcoloring and converting with different artistic effects, and achieve the purpose of transforming simple stickfigures into actual object images.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...