Super Resolution Poster Generation Model Based on Adversarial Generative Network

Authors

  • Jinxuan Li School of Mathematics and Statistics, Guangdong University of Technology, Guangzhou 510006, Guangdong, China
  • Xiuqin Deng School of Mathematics and Statistics, Guangdong University of Technology, Guangzhou 510006, Guangdong, China

DOI:

https://doi.org/10.53469/jtpms.2025.05(6).10

Keywords:

Text image generation, Adversarial generative networks, Deep learning, Image Generation

Abstract

With the continuous advancement of computer technology, image generation technology is also developing rapidly. This article proposes a poster generation method using Chinese text as input, which improves the second stage of the StackGan model to a super-resolution model (GAN_SR3). We introduce the CLIP model to map Chinese text to high-dimensional encoding, improving the matching degree between text and image. By inputting encoding and random noise in the first stage of StackGan, low resolution images are generated and then fed into the improved super-resolution model SR3 to obtain high-resolution posters. Compared with other models on the self built dataset, the experimental results showed that GAN_SR3 achieved higher Inception Score and smaller FID on the movie poster and online poster datasets.

References

Pal, P. et al. 2025. AI-Based Credit Risk Assessment and Intelligent Matching Mechanism in Supply Chain Finance. Journal of Theory and Practice in Economics and Management. 2, 3 (May 2025), 1–9. DOI:https://doi.org/10.5281/zenodo.15368771

Peng, Qucheng, Ce Zheng, and Chen Chen. "Source-free domain adaptive human pose estimation." Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023.

Pinyoanuntapong, Ekkasit, et al. "Gaitsada: Self-aligned domain adaptation for mmwave gait recognition." 2023 IEEE 20th International Conference on Mobile Ad Hoc and Smart Systems (MASS). IEEE, 2023.

Zheng, Ce, et al. "Diffmesh: A motion-aware diffusion framework for human mesh recovery from videos." 2025 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, 2025.

Zhang, Shengyuan, et al. "Research on machine learning-based anomaly detection techniques in biomechanical big data environments." Molecular & Cellular Biomechanics 22.3 (2025): 669-669.

Fang, Z. (2025). Adaptive QoS‐Aware Cloud–Edge Collaborative Architecture for Real‐Time Smart Water Service Management.

Qi, R. (2025). Interpretable Slow-Moving Inventory Forecasting: A Hybrid Neural Network Approach with Interactive Visualization.

Wang, Y. (2025). RAGNet: Transformer-GNN-Enhanced Cox–Logistic Hybrid Model for Rheumatoid Arthritis Risk Prediction.

Zhou, Dianyi, et al. "Research on LSTM-driven UAV path planning." Fourth International Conference on Advanced Algorithms and Neural Networks (AANN 2024). Vol. 13416. SPIE, 2024.

Yang, W., Zhang, B., & Wang, J. (2025). Research on AI Economic Cycle Prediction Method Based on Big Data.

Tu, T. (2025). Log2Learn: Intelligent Log Analysis for Real-Time Network Optimization.

Ding, Y., Wang, X., Yuan, H., Qu, M., & Jian, X. (2025). Decoupling feature-driven and multimodal fusion attention for clothing-changing person re-identification. Artificial Intelligence Review, 58(8), 1-26.

Wang, Lizhe, et al. "Loading capacity prediction of the auxetic tubular lattice structures by multiscale shakedown analysis." Composite Structures 314 (2023): 116938.

Downloads

Published

2025-06-20

How to Cite

Li, J., & Deng, X. (2025). Super Resolution Poster Generation Model Based on Adversarial Generative Network. Journal of Theory and Practice of Management Science, 5(6), 50–57. https://doi.org/10.53469/jtpms.2025.05(6).10