A learned LSTM pipeline recovers 3D bouncing-ball trajectories from monocular 2D tracks by predicting heights on camera rays and then refining the 3D points; it generalizes from simulation to real sports footage.
Synthnet: Leveraging synthetic data for 3d trajectory estimation from monocular video
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Where Is The Ball: 3D Ball Trajectory Estimation From 2D Monocular Tracking
A learned LSTM pipeline recovers 3D bouncing-ball trajectories from monocular 2D tracks by predicting heights on camera rays and then refining the 3D points; it generalizes from simulation to real sports footage.