KD-tree
2 stories filed under KD-tree on Beyond Market Intelligence. The newest of them: “Whitetree: smarter nearest-neighbor search for streaming sensor data” and “From two X-rays, an AI model reconstructs a 3D femur without CT scans.”. A dynamic exact index for streaming nearest-neighbor search is rare, and whitetree makes a strong case for it. Recovering a 3D femur from two X-ray views without CT or a neural network is a bold constraint, and this pipeline makes it work. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work… The list below is every KD-tree story on Beyond Market Intelligence, newest first.

Whitetree: smarter nearest-neighbor search for streaming sensor data
A dynamic exact index for streaming nearest-neighbor search is rare, and whitetree makes a strong case for it. The key insight: scipy's cKDTree has a fixed per-query cost, so maintaining several small trees beats rebuilding one large one. The numbers are compelling, especially the 1,100 steps per second on a 200k-point sliding window. It's a practical, well-measured contribution, and the open question about missed benchmarks is worth exploring.

From two X-rays, an AI model reconstructs a 3D femur without CT scans.
Recovering a 3D femur from two X-ray views without CT or a neural network is a bold constraint, and this pipeline makes it work. The real battle was correspondence: KD-tree hit 50.7x roughness, CPD 28.2x, and only ShapeWorks passed the 5x acceptance gate at 3.3x. That patience paid off, with 0.86 to 1.43mm accuracy on held-out cases. The sigma annealing insight, tying it to camera extent, is a subtle fix with outsized impact. For deeper geometry lessons, our piece on scipy's KD-tree offers adjacent insight.