Motion blur reduces the sharpness and clarity of fast-moving objects, making object detection significantly more challenging. In sports, this effect often transforms a ball from a distinct dot into a streak, complicating its precise localization. The standard labeling convention defines the ball’s position at the front edge of the blur streak, introducing asymmetry into the detection process and disregarding valuable motion blur information that directly correlates with velocity. In this pa- per, we propose a new labeling convention that positions the ball at the midpoint of the blur streak whenever blur is present and explicitly includes motion blur attributes. We demonstrate that this labeling strategy improves detection performance across all tested models for table tennis ball tracking. Additionally, we introduce the first model capable of jointly estimating both ball position and blur characteristics. By leveraging blur information, our approach enables earlier and more accurate trajectory prediction, paving the way for improved tracking in high-speed sports.