Dynamic Optimization Technique for Enhancing 3D Animation Production in the Era of Big Data

ABSTRACT The emergence of advanced 3D animation production processes necessitates optimization techniques capable of managing extensive rendering, motion generation, and computational resource distribution due to the prevalence of massive datasets. Traditional solutions are limited by high computing costs, suboptimal performance, and scalability issues, leading to the adoption of smart, data‐driven alternatives. The research describes a Dynamic Optimization Technique (DOT) which is a synergistic combination of Graph Neural Networks (GNNs), Proximal Policy Optimization (PPO), and Genetic Algorithms (GAs) to optimize the efficiency, realism, and use of resources in 3D animation creation. The process begins with the acquisition of high‐resolution 3D models, motion capture videos, texture maps, and environmental details. The following data hygiene steps include Gaussian filtering to reduce image noise and the use of Local Binary Patterns to obtain salient texture features, and dimensionality reduction in the form of Principal Component Analysis to help provide computationally practical representations of features. Empirical analyses show that the DOT framework would achieve a significant increase in key performance indicators with an accuracy of 97.4. The proposed DOT represents a significant advancement in animation production, offering a flexible and intelligent architecture suitable for real‐time animation, interactive gaming, and immersive virtual reality applications.