In the process of generating personalized poster content, there are often problems such as inconsistency, blurring, and distortion between the generated image and the original image content, exaggerated image styles that do not meet the personalized needs of users. In response to these issues, this article aims to use Pix2Pix Conditional Generative Adversarial Network (Pix2Pix-CGAN) to solve problems such as image blur, distortion, and content inconsistency in personalized poster generation, in order to improve the quality of generated images and meet users’ personalized needs. This article combined L1 loss and adversarial loss optimization models, proposed a style transfer mechanism for personalized poster generation models based on Pix2Pix, and proposed corresponding detail enhancement strategies. The U-Net architecture was used to improve the generator structure, and PatchGAN was used to ensure local detail clarity and image quality. The experimental results showed that the color consistency (CC) of the personalized poster generation model based on Pix2Pix was 0.97, the Style Preservation Index (SPI) was 0.93, the PSNR was 35 dB, and the SSIM was 0.92. The Detail Enhancement Factor (DEF) was 0.88, and the high-frequency component recovery (HFCR) was 0.09, which was at an excellent level compared to other style transfer methods and detail enhancement strategies. The results of this study indicate that the personalized poster generation model based on Pix2Pix exhibits significant advantages in style transfer and detail enhancement, effectively improving the quality of generated images and meeting users' personalized needs.
YangSJiangLLiuZ, et al.Vtoonify: controllable high-resolution portrait video style transfer. ACM Trans Graph2022; 41(6): 1–15.
2.
ZhangZWeiFLiangG, et al.Graphic style transfer technology in multimedia communication: an application of deep residual adaptive networks in graphic design. Int J Commun Network Inf Secur2024; 16(1): 198–210.
3.
MaZLinTLiX, et al.Dual-affinity style embedding network for semantic-aligned image style transfer. IEEE Transact Neural Networks Learn Syst2022; 34(10): 7404–7417.
4.
SiddiganTMSudharsanGRamAGS. Pixelforge: image revamping through text and image input using pix2pix. In: Advances in Networks, Intelligence and Computing. Milton: Taylor & Francis Group, pp. 555–561.
5.
WangHZhangZZhuQ, et al.Batch skeleton extraction from ESPI fringe patterns using pix2pix conditional generative adversarial network. Opt Rev2022; 29(2): 97–105.
6.
EkerGAPehlivanoğluKMDuruN, et al.BrainPixGAN: generating intraoperative MRI images with mask-based generative networks. Engineering Science and Technology, an International Journal2024; 58: 101827.
7.
JinDJinZHuZ, et al.Deep learning for text style transfer: a survey. Comput Ling2022; 48(1): 155–205.
8.
GargMUbhiJSAggarwalAK. Neural style transfer for image steganography and destylization with supervised image to image translation. Multimed Tool Appl2023; 82(4): 6271–6288.
9.
DebadyutiMPritamSDmitryK, et al.Brain tumor image generation using an aggregation of GAN models with style transfer. Sci Rep2022; 12(1): 9141.
10.
XinyingHYangWRuiW. A method for style transfer from artistic images based on depth extraction generative adversarial network. Appl Sci2023; 13(2): 867.
11.
WangLWangLChenS. ESA‐CycleGAN: edge feature and self‐attention based cycle‐consistent generative adversarial network for style transfer. IET Image Process2022; 16(1): 176–190.
12.
LiuMZhuAHMaitiP, et al.Style transfer generative adversarial networks to harmonize multisite MRI to a single reference image to avoid overcorrection. Hum Brain Mapp2023; 44(14): 4875–4892.
13.
LiuSZhangQHuangL. Edge computing-based Generative Adversarial Network for photo design style transfer using conditional entropy distance. Comput Commun2023; 210: 174–182.
14.
TianCYuanYZhangS, et al.Image super-resolution with an enhanced group convolutional neural network. Neural Network2022; 153: 373–385.
15.
ZamirSWAroraAKhanS, et al.Learning enriched features for fast image restoration and enhancement. IEEE Trans Pattern Anal Mach Intell2022; 45(2): 1934–1948.
16.
MehranianAWollenweberSDWalkerMD, et al.Image enhancement of whole-body oncology [18F]-FDG PET scans using deep neural networks to reduce noise. Eur J Nucl Med Mol Imag2022; 49(2): 539–549.
17.
DaihongJSaiZLeiD, et al.Multi-scale generative adversarial network for image super-resolution. Soft Comput2022; 26(8): 3631–3641.
18.
MingqiangGZeyuanZHengL, et al.NDSRGAN: a novel dense generative adversarial network for real aerial imagery super-resolution reconstruction. Rem Sens2022; 14(7): 1574.
19.
SunCGuDZhangY, et al.Vision‐based displacement measurement enhanced by super‐resolution using generative adversarial networks. Struct Control Health Monit2022; 29(10): e3048.
20.
LiuZLiZWuX, et al.DSRGAN: detail prior-assisted perceptual single image super-resolution via generative adversarial networks. IEEE Trans Circ Syst Video Technol2022; 32(11): 7418–7431.
21.
WangYLiXNanF, et al.Image super-resolution reconstruction based on generative adversarial network model with feedback and attention mechanisms. Multimed Tool Appl2022; 81(5): 6633–6652.
22.
YongyangXWeiLAnnaH, et al.TE-SAGAN: an improved generative adversarial network for remote sensing super-resolution images. Rem Sens2022; 14(10): 2425.
23.
WenJZhuXRWangCD, et al.A framework for personalized recommendation with conditional generative adversarial networks. Knowl Inf Syst2022; 64(10): 2637–2660.
24.
EsmaeiliMKianiK. Generating personalized facial emotions using emotional EEG signals and conditional generative adversarial networks. Multimed Tool Appl2024; 83(12): 36013–36038.
25.
DingXWangYXuZ, et al.Continuous conditional generative adversarial networks: novel empirical losses and label input mechanisms. IEEE Trans Pattern Anal Mach Intell2022; 45(7): 8143–8158.
26.
AalaeiMSaadiMRahbarM, et al.Architectural layout generation using a graph-constrained conditional generative adversarial network (GAN). Autom ConStruct2023; 155: 105053.
27.
MehmoodMAlshammariNAlanaziSA, et al.Improved colorization and classification of intracranial tumor expanse in MRI images via hybrid scheme of Pix2Pix-cGANs and NASNet-large. Journal of King Saud University-Computer and Information Sciences2022; 34(7): 4358–4374.
28.
GalRArarMAtzmonY, et al.Encoder-based domain tuning for fast personalization of text-to-image models. ACM Trans Graph2023; 42(4): 1–13.
29.
NitzanYAbermanKHeQ, et al.Mystyle: a personalized generative prior. ACM Trans Graph2022; 41(6): 1–10.
30.
HanDLiLGuoX, et al.Multi-exposure image fusion via deep perceptual enhancement. Inf Fusion2022; 79: 248–262.
31.
TodaRTeramotoAKondoM, et al.Lung cancer CT image generation from a free-form sketch using style-based pix2pix for data augmentation. Sci Rep2022; 12(1): 12867.
32.
DashAYeJWangG, et al.High resolution solar image generation using generative adversarial networks. Ann Data Sci2022; 11: 1–17.
33.
ZhaoXYuHBianH. Image to image translation based on differential image Pix2Pix model. Comput Mater Continua (CMC)2023; 77(1): 181–198.
34.
ZhangY. A review of image style transfer using generative adversarial networks techniques. Anal Metaphys2024; 23: 131–142.
35.
ElasriMElharroussOAl-MaadeedS, et al.Image generation: a review. Neural Process Lett2022; 54(5): 4609–4646.
36.
HuZLeeRKWAggarwalCC, et al.Text style transfer: a review and experimental evaluation. SIGKDD Explor Newsl2022; 24(1): 14–45.
37.
ChenGZhangGYangZ, et al.Multi-scale patch-GAN with edge detection for image inpainting. Appl Intell2023; 53(4): 3917–3932.
38.
FanCLinHQiuY. U-Patch GAN: a medical image fusion method based on GAN. J Digit Imag2023; 36(1): 339–355.
39.
GeXTanJZhangL, et al.Blind image deblurring with Gaussian curvature of the image surface. Signal Process Image Commun2022; 100: 116531.
40.
ShahABangashJIKhanAW, et al.Comparative analysis of median filter and its variants for removal of impulse noise from gray scale images. Journal of King Saud University-Computer and Information Sciences2022; 34(3): 505–519.
