AIGC in Film and Television Special Effects Production: 
Problems and Solutions

Yunting Heng

doi:10.70711/rcha.v3i6.7595

AIGC in Film and Television Special Effects Production: Problems and Solutions

Yunting Heng

Abstract

This paper aims to investigate the current applications, challenges, and corresponding strategic solutions associated with Artificial Intelligence Generated Content (AIGC) in the domain of visual effects (VFX) production for film and television. Leveraging text-toimage generation technologies, AIGC has significantly streamlined the VFX production pipeline and enhanced creative efficiency. While
demonstrating remarkable efficacy in reducing labor costs, AIGC continues to encounter performance bottlenecks when processing highresolution, high-fidelity content. Furthermore, critical technical challengesincluding limitations inherent in Generative Adversarial
Networks (GANs), issues of semantic consistency, refinement of fine-grained details in image synthesis, and substantial computational
resource demandsremain pressing concerns. To address these challenges, this study proposes a comprehensive set of solutions: technological advancement through diffusion model-based iterations, cross-modal data fusion to improve the quality of multimodal information
integration, the incorporation of user feedback mechanisms for bias mitigation and stylistic customization, and model compression techniques to alleviate computational overhead.

Keywords

AIGC; Film and Television; Special Effects Production

Full Text:

PDF

Included Database

References

[1] Y. Peng, X. Meng, Y. Li, and L. Liu, "Image Super-Resolution Reconstruction Combining Coordinate Attention and Generative Adversarial Networks, " Computer Engineering and Science, vol. 46, no. 1, pp. 122131, 2024.

[2] S. Wang and B. Chen, "Technological Fantasy and Human Revelation: The Dual Construction of Artificial Intelligence Images in Science Fiction Films, " Film Literature, no. 18, pp. 6066, 2024.

[3] Z. Xie, "Research on Technological Imagery in the History of Chinese Science Fiction Films, " Southern Forum, no. 6, pp. 8687, 2020.

[4] Q. Zhang, "Research on Image Generation Methods for Computer Vision Systems Based on AICG Technology, " Information Recording

Materials, vol. 26, no. 5, pp. 145147, 2025.

[5] Z. Wang and X. Li, "Precise Object Removal Based on Semantic Consistency, " Computer and Digital Engineering, vol. 53, no. 1, pp.

234239, 2025.

[6] H. Wang, R. Zhang, and Y. Huang, "Spread Spectrum and Conventional Modulation Signal Recognition Method Based on Generative

Adversarial Network and Multimodal Attention Mechanism, " Journal of Electronics and Information Technology, vol. 46, no. 4, pp.

12121221, 2024.

[7] Y. Liu and K. Mao, "Small-Difference Image Texture Feature Information Retrieval Based on Adaptive Feedback Mechanism, " Journal

of Jiangsu University (Natural Science Edition), vol. 46, no. 1, pp. 7381, 2025.

[8] X. Li and Q. Chen, "2D-3D Coupled Network for Multimodal Data Fusion in 3D Scene Segmentation, " Computer Era, no. 1, pp. 17

25, 2023.

[9] F. Guan, H. Zhang, S. Lu, H. Lai, X. Du, and Y. Zheng, "Research Status of Diffusion Models in the Field of Computer Vision, " CAAI

Transactions on Intelligent Systems, vol. 20, no. 2, pp. 265282, 2025.

[10] H. Xing, T. Kuang, L. Xu, Y. Li, D. Zheng, S. Luo, P. Dai, K. Li, and L. Feng, "Image Semantic Communication Method Based on Contrastive Learning and Diffusion Models, " Chinese Journal of Computers*, vol. 48, no. 5, pp. 11511167, 2025.

[11] X. Zuo, Z. Tian, M. Yin, L. Dang, B. Qiao, Y. Liu, and Y. Xie, "Research on Remote Sensing Super-Resolution Image Generation Based

on Residual Diffusion Models, " Journal of Henan Normal University (Natural Science Edition), vol. 53, no. 3, pp. 5865, 2025.

DOI: http://dx.doi.org/10.70711/rcha.v3i6.7595

Refbacks

There are currently no refbacks.