Journal of Engineering, Project, and Production Management, 2026, 16(6), 2026-79
Automated Shadow Decomposition for Animation Production Workflows Based on Hybrid Smooth and Shadow Networks
Lecturer, School of Art, Zhengzhou Business University, Gongyi, 451200, China, E-mail: jiaobo2025@126.com
Production Management
Received January 21, 2026; revised March 18, 2026; August 4, 2026; accepted September 7, 2026
Available online September 20, 2026
Abstract: In modern digital animation production, with continuous technological advancements, especially innovations in computer graphics and artificial intelligence, the efficiency and quality of the animation production process have become key factors in the competitiveness of production companies. However, despite the rapid development of rendering technologies and image generation algorithms, shadow processing remains a complex and time-consuming challenge. To address operational bottlenecks and high manual labor costs in digital animation production pipelines, this study presents an automated shadow-decomposition framework to optimize post-production workflows. To overcome the challenge of separating shadows and reflectance in dynamic animation, this study develops an animation shadow decomposition model that employs a hybrid smoothing network and a shadow network. The hybrid smoothing module improves the distinction between shadows and base color layers by smoothing multi-scale features, and the shadow network introduces a temporal consistency loss to further optimize shadow coherence between frames. Experimental outcomes reveal that in the reflectance separation task, the model attains a peak signal-to-noise ratio of 34.27 dB, a structural similarity index of 0.956, a temporal consistency of 0.943, and a temporal error of 0.048. For rendering pipeline developers and technical specialists, practical validation confirms that the model directly optimizes the animation production workflow. By enhancing temporal coherence, it systematically replaces manual rotoscoping and frame-correction efforts with a standardized, automated process. This shift allows practitioners to reallocate human resources from repetitive corrective tasks to high-value creative stages, fundamentally improving the reliability, cost-efficiency, and throughput of post-production engineering. By automating the shadow-reflectance separation, the model significantly reduces the reliance on frame-by-frame manual masking, offering a cost-effective solution that enhances rendering efficiency by shortening the iterative feedback loop in the animation editing workflow. This research aligns with emerging digital production standards for automated workflows. By providing a robust AI-assisted framework, it contributes to the governance of automated tools in creative industries, addressing the impact of automation on workforce efficiency and digital asset management policy. Future research will focus on the model’s scalability within cloud-based production architectures and its long-term impact on digital asset reuse.
Keywords: Animated shadows; hybrid smooth network; temporal consistency; production workflow optimization; digital rendering systems.
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: Jiao, B. (2026). Automated Shadow Decomposition for Animation Production Workflows Based on Hybrid Smooth and Shadow Networks. Journal of Engineering, Project, and Production Management, 16(6), 2026-79.
