Visual glitches reduce player immersion and compromise product quality, making automated detection a vital component of modern game quality assurance (QA) processes. Manual testing remains costly and difficult to scale while existing AI-based methods often cannot generalize to the wide variety of rendering styles and gameplay scenarios. To address these challenges, a hierarchical detection model is introduced, augmented with game state information to improve contextual sensitivity. A synthetic data generation pipeline is proposed to produce diverse, game-specific datasets, supporting model adaptation to varying visual environments and edge cases. This process is supported by human-in-the-loop techniques that guide the collection of critical samples. Additionally, the framework continuously monitors and evaluates rendering outputs during development, enabling early detection of visual glitches in production workflows. Human oversight further contributes to the design of targeted visual test scenarios, improving detection effectiveness during continuous development cycles. Results from large-scale deployments with industry partners demonstrate the practicality of the system.

Creating synthetic behaviors of vehicles in simulation applications has always been challenging from a development standpoint. First, it is a real challenge to create a credible and realistic simulation while achieving the required runtime efficiency. Second, the effort required to implement it can add significant cost to the development processes. In this paper, we propose an automated way to design vehicle simulation systems by transfer learning from reality to simulators. Our methods rely on advanced deep learning technologies and datasets commonly used in the field of self-driving cars. To assess how well this approach would work in a simulation environment, experiments using the CARLA simulator are presented in the evaluation. The results show that the proposed transfer learning approach provides good results, both quantitatively and qualitatively, and is suitable for runtime evaluation even in resource-constrained simulation applications such as video games.