A Novel Synthetic Dataset for Broadcast Motorsports Scene Understanding

Utilizing the CARLA (Car Learning to Act) simulation environment, a high-fidelity dataset for racecars pose estimation is constructed, incorporating diverse lighting conditions, occlusions, and dynamic camera perspectives to enhance model generalization. A multi-stage data refinement pipeline is introduced to mitigate the impact of extreme occlusions and irrelevant samples while preserving the complexity of real-world challenges.