High-performance EVT3 (EVT 3.0) decoder for Prophesee / Metavision event cameras. Read .raw and HDF5 event data into NumPy, CSV or Rust — 1.62x faster than the C++ reference, byte-identical output. CLI, Python bindings and Rust library for event-based vision and neuromorphic research.
Lossless compression for neuromorphic event-camera data. 47.6× / 1.51 bpe / 0.55 ms per N-MNIST sample. First shipping product of the Mirror Fractal Method. Patent pending. Live demo: codec.mirrorfractal.com