Mirror Fractal · Codec
MMXXVI v0.3.29
Research · Paper · DOI · Reproducible
ORCID 0009-0002-3921-0868
For researchers and reviewers

Research artefacts

Everything needed to reproduce the headline numbers — paper, DOI, machine-readable citation, public mirror, and a 5-minute repro guide on the full N-MNIST training set.

02 / N-MNIST · full set

Numbers, all 60 000 samples

Lossless on every digit, every sample. Encode times measured native on a single thread; the browser demo runs the same encoder at ~8× the latency due to single-threaded WASM.

Digit Samples Avg events Ratio Bits / event Encode
05,9235,44453.4×1.350.65 ms
16,7422,43236.6×1.970.42 ms
25,9584,70850.3×1.430.58 ms
36,1314,70350.4×1.430.58 ms
45,8423,79444.4×1.620.54 ms
55,4214,37248.7×1.480.56 ms
65,9184,21547.7×1.510.55 ms
76,2653,68745.2×1.590.52 ms
85,8514,70250.0×1.440.58 ms
95,9493,92746.1×1.560.52 ms
Total 60,000 4,172 47.6× 1.51 0.55 ms
03 / Reproduce

N-MNIST in five minutes

Identical pipeline to the table above. The aggregate numbers are deterministic — repeated runs give bit-for-bit identical outputs.

# 1. Install
pip install mfc-codec

# 2. Get the N-MNIST training set (~290 MB)
# https://www.garrickorchard.com/datasets/n-mnist
mkdir -p data/nmnist && cd data/nmnist
# unpack the 60,000-sample 'Train' folder here

# 3. Run the bundled benchmark
python -m mfc.examples.nmnist_bench --data data/nmnist/Train

# expected (last line):
# total=60000  ratio=47.6x  bpe=1.51  encode=0.55ms  lossless=true

Run on any modern CPU; the benchmark is single-threaded by design so numbers compare directly to the paper. For DSEC (automotive 640×480), use mfc.examples.dsec_load on a Zurich-city snippet — the paper reports 9.2× / 7.85 bpe on a 500 000-event window.

04 / Datasets

Tested recordings

  • N-MNIST — Orchard et al. — 60 000 samples, 34×34 sensor, all digits.
  • DSEC (Zurich automotive) — 640×480 stereo event cameras, 500 000-event windows.
  • MVSEC — planned for the next benchmark refresh.
  • Synthetic — DVS128 through 1280×720 HD ranges, 100 k to 2 M events per frame, in the paper's Table 2.
05 / Citation

Cite this work

@software{mfc_codec_2026,
  author  = {Solonskii, Aleksei},
  title   = {Mirror Fractal Codec: Lossless Compression for Neuromorphic Event Camera Streams},
  year    = {2026},
  version = {0.3.29},
  doi     = {10.5281/zenodo.19704064},
  url     = {https://codec.mirrorfractal.com}
}

Working on a paper that uses MFC? Drop us a line at info@mirrorfractal.com — we keep an early-access channel for ongoing research and can answer property questions about the codec under the same terms as the paper.