mfc-codec 0.3.28

Mirror Fractal Codec — lossless compression for neuromorphic event camera data

Mirror Fractal Codec

Lossless compression for neuromorphic event-camera data (DVS/ATIS).

1.51 bits/event · 47.6x compression · 0.55 ms per N-MNIST sample.

Patent Pending — US Provisional #64/034,974

Install

pip install mfc-codec

Pre-built wheels for CPython 3.11 on Linux (manylinux_2_34 x86_64), macOS (arm64), and Windows (amd64).

Quick start

import mfc

events = mfc.load_nmnist("sample.bin")
compressed, stats = mfc.compress(events, width=34, height=34, t_bits=16, xy_bits=8)
print(f"{stats.compression_ratio:.1f}x, {stats.bits_per_event:.2f} bpe")

decoded = mfc.decompress(compressed)
assert events == decoded   # bit-exact, lossless

Results

N-MNIST (60,000 real samples, 34×34 sensor)

Digit	Samples	Avg events	Ratio	bpe	Encode
Total	60,000	4,172	47.6×	1.51	0.55 ms

High-resolution synthetic

Config	Events	Raw	Compressed	Ratio	Encode
DVS128 500K	500K	4,395 KB	3.9 KB	1,117×	4.9 ms
VGA 2M	2M	17,578 KB	20.0 KB	878×	36.9 ms
HD 1M	1M	8,789 KB	8.5 KB	1,040×	58.2 ms

Supported dataset formats

N-MNIST .bin · AEDAT 2.0 .aedat · DSEC HDF5 (Blosc/LZ4/zstd) · .npy · .evb · CSV · .dat/.raw

Links

• Live demo — https://codec.mirrorfractal.com
• Public repository (docs, examples, issues) — https://github.com/MirrorFractal/codec
• Paper / Zenodo deposit — DOI: ZENODO_DOI_PENDING

Citation

@software{mfc_codec_2026,
  author = {Solonskii, Aleksei},
  title  = {Mirror Fractal Codec: Lossless Compression for Neuromorphic Event Camera Streams},
  year   = {2026},
  doi    = {ZENODO_DOI_PENDING},
  url    = {https://codec.mirrorfractal.com}
}

License

Proprietary — all rights reserved. Patent Pending US 64/034,974.

Contact: [e-mail]