Image style transfer is a research hotspot in the field of computer vision.For this job,many approaches have been put forth.These techniques do,however,still have some drawbacks,such as high computing complexity and c...Image style transfer is a research hotspot in the field of computer vision.For this job,many approaches have been put forth.These techniques do,however,still have some drawbacks,such as high computing complexity and content distortion caused by inadequate stylization.To address these problems,PhotoGAN,a new Generative AdversarialNetwork(GAN)model is proposed in this paper.A deeper feature extraction network has been designed to capture global information and local details better.Introducingmulti-scale attention modules helps the generator focus on important feature areas at different scales,further enhancing the effectiveness of feature extraction.Using a semantic discriminator helps the generator learn quickly and better understand image content,improving the consistency and visual quality of the generated images.Finally,qualitative and quantitative experiments were conducted on a self-built dataset.The experimental results indicate that PhotoGAN outperformed the current state-of-the-art techniques.It not only performed excellently on objective metrics but also appeared more visually appealing,particularly excelling in handling complex scenes and details.展开更多
基金funded by the Key R&D and Transformation Projects of Xizang(Tibet)Autonomous Region Science and Technology Program(funder:the Department of Science and Technology of the Xizang(Tibet)Autonomous Region),funding(grant)number:XZ202401ZY0004.
文摘Image style transfer is a research hotspot in the field of computer vision.For this job,many approaches have been put forth.These techniques do,however,still have some drawbacks,such as high computing complexity and content distortion caused by inadequate stylization.To address these problems,PhotoGAN,a new Generative AdversarialNetwork(GAN)model is proposed in this paper.A deeper feature extraction network has been designed to capture global information and local details better.Introducingmulti-scale attention modules helps the generator focus on important feature areas at different scales,further enhancing the effectiveness of feature extraction.Using a semantic discriminator helps the generator learn quickly and better understand image content,improving the consistency and visual quality of the generated images.Finally,qualitative and quantitative experiments were conducted on a self-built dataset.The experimental results indicate that PhotoGAN outperformed the current state-of-the-art techniques.It not only performed excellently on objective metrics but also appeared more visually appealing,particularly excelling in handling complex scenes and details.
