Optical flow models excel on synthetic benchmarks but can struggle with real-world scenarios involving large displacements, which are critical for applications like autonomous navigation and augmented reality. To address this, we introduce a novel real-world dataset and evaluation framework, using a specialized annotation tool to capture ground truth optical flow in scenarios with fast movements and close-range objects. Our approach minimizes confounders, providing clear insights into model performance with large displacements. Findings show recent models outperform the previous state-of-the-art, RAFT, across all tested scenarios. Both the annotation tool and dataset are available to support further research.

This paper investigates the use of Adaptive Procedural Content Generation (APCG), a form of procedural content generation that is adjusted to a player model, to tailor educational content based on individual learner profiles, thereby improving engagement and consequent learning outcomes. Key research questions include how to measure the success of APCG, its impact on academic performance, and the comparative advantages over traditional PCG methods. Through a literature review, this study identifies current trends, methodologies, and challenges in the application of APCG in educational settings. A list of existing papers has been synthesized on the knowledge body that exists on APCG implementations. We present these findings together with their most relevant methods, domains, target demographics and conclusions to gain an in- sight in which research currently exists on it. The findings aim to provide insights for educators, game developers, and researchers on effective implementations of APCG, paving the way for more personalized and impactful educational technologies.