| title | FMT: Lossless Image Compression in a Fixed Number of Parallel Steps |
|---|---|
| authors | Ammar Ali |
| date | 2026-11-17 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2611.23108 |
| affiliation | Lab of Efficient AI and Data |
| upvotes | 10 (Hugging Face Daily Papers, 2026-11-19) |
| links | abs pdf hf |
| cite | |
| abstract | Learned lossless codecs make smaller files than common classical codecs, yet the images we archive and train on still use classical codecs. A main reason is time: a learned codec takes seconds to decode a photo that a classical codec opens in milliseconds, and their faster variants give up most of their gain in size. We argue that much of this time is spent waiting, not computing: the network waits for the values it conditions on, and the arithmetic decoder reads them one at a time. We introduce FMT (Fixed-step Multiscale Tree), a lossless image format whose decoding order and entropy coder are designed together so that neither wait grows with the image. FMT stores an image as a coarse-to-fine tree whose steps hold independent values: a GPU predicts each step at once and decodes it in parallel rANS lanes that carry their states from step to step, so an image of any size decodes in a fixed number of sequential steps. On this tree we build a family of bit-exact codecs, from a rule with no network to large networks, and no codec we ran on the same GPU beats any of them on both size and speed. Without a network, FMT beats NVIDIA's HTJ2K on size and speed; with a large one, it decodes Kodak photos 9 to 61X faster than learned codecs we ran on the same A100, at the same size or smaller. |
bibtex
@misc{ali2026fmt,
title={FMT: Lossless Image Compression in a Fixed Number of Parallel Steps},
author={Ammar Ali},
year={2026},
eprint={2611.23108},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2611.23108}
}