Effxcts

sports and technology

[Effxcts @EffxctsLLC]

🚨 Just built a system that reconstructs 4D NBA plays from a single broadcast video.

📦 Pipeline includes:
• Object Detection
• Camera Stabilization
• Pose Tracking
• Homography
• Ball Path

See more examples on my page—happy to answer any questions below.

[march maddyness 💥 @phxsunz25]

the one singular ball in vegas is so funny to me for no reason

[Los Angeles Lakers @Lakers]

Longevity.

[Kirk Goldsberry @kirkgoldsberry]

83

[Effxcts @EffxctsLLC]

@yanpei_cao Very cool. Does it work with photorealistic humans?

[Effxcts @EffxctsLLC]

@1littlecoder check my pinned post for 3D pose reconstruction of nba plays

[Effxcts @EffxctsLLC]

@ChrisAtKIRI Does it work well on a headshot?

[Effxcts @EffxctsLLC]

@skalskip92 @903124S example of stabilized clip with poses

[Effxcts @EffxctsLLC]

@skalskip92 @903124S yes I figured it would be tough to have an accurate model for court key point detection. stabilizing the camera in the pipeline with third-party software like After Effects makes it a lot easier. there might be other options for closer to real-time stabilization

[Effxcts @EffxctsLLC]

@903124S @skalskip92 yes i detect jumps and then interpolate from beginning of jump position to end of jump position in the homography. and then i use the time of the jump to determine z height

[Effxcts @EffxctsLLC]

@skalskip92 @903124S yes this was before your nba keypoint detection model was out and I didn’t want to create a dataset to train a model lol

[Effxcts @EffxctsLLC]

@ODJ__ vitpose+-h

[Effxcts @EffxctsLLC]

real hoopers know whose POV this is

[Effxcts @EffxctsLLC]

@CrumpledJumper 😂

[Effxcts @EffxctsLLC]

All of Jokic’s career FG visualized

[Effxcts @EffxctsLLC]

All of Tatum’s career FG visualized

[Effxcts @EffxctsLLC]

@SkyedOKC More 3d data visualizations on the way 👈

[Effxcts @EffxctsLLC]

All of SGA’s career FG visualized