llnl/LEAP

comprehensive library of 3D transmission Computed Tomography (CT) algorithms with Python and C++ APIs, a PyQt GUI, and fully integrated with PyTorch

44
/ 100
Emerging

LEAP implements high-accuracy forward and back projectors via CUDA kernels optimized for multi-GPU and multi-core CPU execution, with PyTorch bindings enabling fully differentiable CT operations for end-to-end learning. The library includes physics-based correction algorithms (scatter, beam hardening, dual-energy decomposition) through integration with XrayPhysics, and demonstrates superior reconstruction quality—achieving 1.7× higher SNR than comparable packages like ASTRA on standard benchmarks.

220 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

220

Forks

28

Language

Cuda

License

MIT

Last pushed

Sep 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/llnl/LEAP"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.