Skip to content
Open access

Animation Storyboard Dynamic Layout and Rhythm Control Strategy Based on Optimized Reinforcement Learning

Sep 2026 · International Journal of e-collaboration · 0 citations · 17 references

Abstract

This research presents a Dynamic Shuffled Frog Leaping Fine-tuned Adaptive Soft Actor-Critic (DSFL-ASAC) model capable of dynamically adjusting frame composition (layout) and controlling temporal transitions (rhythm) between AI-assisted storyboard panels. A dataset comprising animation scripts, existing storyboards, and annotated visual sequences is collected. Data preprocessing involves Z-score normalization and the application of noise filters to smooth rhythm-based moving averages and reduce abrupt timing changes. For visual layout, features are extracted using Convolutional Neural Networks (CNNs) to capture spatial composition, while rhythm-related features are extracted using Mel-Frequency Cepstral Coefficients (MFCCs). The results show that this approach reduced production time and cognitive load for animators and also enhanced the overall quality of animated storytelling. The evaluation results indicate remarkable improvements in RFI (+31.3%), VER (+18.5%), and LCS (+23.7%), with production time decreased by 35.1% and cognitive load reduced by 37.2%, all statistically significant.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.