Style transfer is a heated computer vision topic that has been broadly mentioned in both academic research and practical applications, for example, the style transfer technique is behind the various filters in daily used image processing tools. However, it had been a major drawback in this field that its training set required strictly paired images, until the introduction of CycleGAN, a combination of style transfer technique and Generating Adversarial Networks (GAN), which has also been one of the most popular technologies in machine learning since its advent. CycleGAN is an image style transfer technique proposed by Jun-Yan Zhu et al. at the University of California, Berkeley. The paper proposed a way that can be performed without the strict pairs of the source image and style image so that a wider range of dataset options can be incorporated into this field. The generator in the CycleGAN network consists of an encoder, converter, and decoder, which can play the role of preserving the original image features and converting images. In our research, this study found that there is still certain scope for improvement in the original model, so this study conducted a further study on the basis of rebuilding the original CycleGAN. This study studied the CycleGAN framework, which is an unsupervised learning style transfer model based on generative adversarial networks, and proposed an improved nerual network model by modifying the adversarial loss, and compared it with the original CycleGAN network. The results showed that the modified CycleGAN can obtain more realistic images with better visual effects than original CycleGAN after training in fewer rounds.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Research on style transfer model based on improved CycleGAN algorithm


    Beteiligte:
    Bi, Xiaoyang (Autor:in) / He, Enhao (Autor:in) / Wang, Qipeng (Autor:in)


    Erscheinungsdatum :

    2023-10-11


    Format / Umfang :

    3146063 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Research on User’s Subjective Preference of Taohuawu New Year Painting Based on CycleGAN

    Dai, Funan / Jiang, Zhengqing / Fang, Yiao et al. | Springer Verlag | 2022


    Based on CycleGAN infrared ship image expansion method

    Liu, Peijie / Zhang, Yan / Shi, Zhiguang et al. | SPIE | 2020


    A Rapid Wind Velocity Prediction Method in Built Environment Based on CycleGAN Model

    Tan, Chuheng / Zhong, Ximing | Springer Verlag | 2023

    Freier Zugriff

    Using CycleGAN to Achieve the Sketch Recognition Process of Sketch-Based Modeling

    Li, Yuqian / Xu, Weiguo | Springer Verlag | 2021

    Freier Zugriff