Journal of Engineering, Project, and Production Management, 2026, 16(4), 2025-252
AI-Assisted Automation of Post-Production Compositing Workflows in Film and Television
1
Lecturer, Luoyang Vocational College of Science and Technology, Luoyang,
471822, China, E-mail: violet.feng888@outlook.com (corresponding
author).
2
Lecturer, Luoyang Vocational College of Science and Technology, Luoyang,
471822, China
Production Management
Received November 3, 2025; revised April 9, 2026; accepted May 2, 2026
Available online May 29, 2026
Abstract: The purpose of this study is to explore efficiency limitations within the post-production process in terms of compositing in films and TV series through an approach that combines AI with automation to optimize processing and image quality. Mixed methods were used in an experiment that involved 24 professional compositors analyzing 150 video clips using an AI-based algorithm featuring Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and transformers. This algorithm was trained using 50,000 professional sequences of composite images. Tests were carried out using commercial algorithms on a standard workstation. Results were obtained that showed considerable enhancements in terms of efficiency for all measures: time saving of 41.7% (processing time of 78.5±12.3 minutes), Peak Signal-to-Noise Ratio (PSNR) increase of 9.7% resulting in 35.2±0.8 dB, and Structural Similarity Index Measure (SSIM) enhancement by 8.0% to 0. This platform maintained real-time performance at 18.4 frames per second while providing significantly better visual output than any currently available commercial system. Overall user satisfaction stood at 8.4/10, and 92% of all artists involved in the study used the software within a week of the following training. This AI-driven platform proves that the use of automation can improve both technical and artistic performance within professional compositing processes.
Keywords: Artificial intelligence, deep learning, film production, post-production compositing, workflow automation.
Copyright © Journal of Engineering, Project, and Production Management (EPPM-Journal).
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.
Requests for reprints and permissions at eppm.journal@gmail.com.
Citation: You, Q. and Zhang, X. (2026). AI-Assisted Automation of Post-production Compositing Workflows in Film and Television. Journal of Engineering, Project, and Production Management, 16(4), 2025-252.
