Bryson DeChambeau Trains With Google Cloud AI That Tracks 30 Body Points Per Swing
DeChambeau uses Google Cloud deep learning models that combine 2D and 3D pose estimation. The system records over 30 anatomical and equipment landmarks at each frame. It then classifies swing phases such as top of backswing, impact, and finish to quantify outcomes.
Athletes learn to replace subjective video review with quantified kinematic data. This shifts practice from feel-based repetition to targeted correction of measurable variables. Workflows now integrate cloud pipelines that return frame-by-frame metrics within seconds.
Bryson DeChambeau partnered with Google Cloud to deploy the AI Crusher pipeline on tournament swings. The setup delivers real-time feedback that DeChambeau uses to adjust club path and body rotation between shots.
Step 1: Upload swing footage to Google Cloud Video AI at https://cloud.google.com/video-intelligence. Step 2: Enable pose estimation and request 2D plus 3D landmark output for at least 30 body and club points. Step 3: Parse the returned JSON to label swing phases and export metrics for each frame.