Interpretable Pre-Release Baseball Pitch Type Anticipation from Broadcast 3D Kinematics
This research provides a large-scale analysis of pre-release pitch type anticipation for baseball analysts and coaches, establishing an empirical ceiling for kinematic-based prediction.
This paper investigates how much a pitcher's body kinematics can reveal about the upcoming pitch type, classifying eight pitch types from 3D pose sequences without ball-flight data. They achieved 80.4% accuracy on 119,561 professional pitches, finding that upper-body mechanics contribute 64.9% of the predictive signal.
How much can a pitcher's body reveal about the upcoming pitch? We study this question at scale by classifying eight pitch types from monocular 3D pose sequences, without access to ball-flight data. Our pipeline chains a diffusion-based 3D pose backbone with automatic pitching-event detection, groundtruth-validated biomechanical feature extraction, and gradient-boosted classification over 229 kinematic features. Evaluated on 119,561 professional pitches, the largest such benchmark to date, we achieve 80.4\% accuracy using body kinematics alone. A systematic importance analysis reveals that upper-body mechanics contribute 64.9\% of the predictive signal versus 35.1\% for the lower body, with wrist position (14.8\%) and trunk lateral tilt emerging as the most informative joint group and biomechanical feature, respectively. We further show that grip-defined variants (four-seam vs.\ two-seam fastball) are not separable from pose, establishing an empirical ceiling near 80\% and delineating where kinematic information ends and ball-flight information begins.