Dance Sage
Dance Sage
Every screen below is real: a salsa couple dancing a side basic, seen as the skeletons Dance Sage works with. Cameras are imperfect — they jitter, and they lose limbs whenever bodies overlap. Dance Sage refines what the camera sees. Four screens per experiment: the dancer’s true movement, what a camera typically delivers, our refinement model, and the same model tuned specifically for dancing. The faint white skeleton everywhere is the true movement — the closer, the better. Drag any screen to spin it. Every number is a real measurement, not an illustration.
A single dancer, the way Dance Sage sees solo practice. The camera’s version shakes; the refined versions don’t.
Two dancers in open hold, exactly where they really stood. Partner dancing is harder for cameras — and where refinement matters most.
Here the camera never sees the leader’s left arm at all — as happens whenever a partner blocks the view. Dance Sage restores the whole arm, shown in gold. The dance-tuned model places it noticeably closer to the truth.
The hardest case in partner dancing: both arms of the hold vanish between the two bodies. Dance Sage restores both dancers’ hidden arms (gold) and keeps the couple whole.
The most realistic case: the arm is visible, disappears for a second (the gold band on the chart), then returns. Watch the gold arm carry the movement across the gap — and how much tighter the dance-tuned model tracks it.
Everything above is measured against a dancer’s true movement, which is how we know the numbers. This is the same analysis on ordinary phone video: our skeleton drawn back onto the clip it came from, and beside it the same seconds in three dimensions. Press play on the video; drag the figure to turn it.
A couple is the hard case, because each dancer keeps hiding the other. Both are held in every frame here, and neither skeleton ever jumps to the wrong body.
A single dancer is the easy case, and this is what the app does on the phone itself, for nothing, while you dance.
Behind every skeleton is a whole body. This is the same close hold as the first pair, as two watertight surfaces of 18,439 points each — switch either dancer off to look inside the hold, or turn on the wireframe to see the surface itself.