FMT: Lossless Image Compression in a Fixed Number of Parallel Steps
Abstract
The Fixed-step Multiscale Tree (FMT) format achieves highly efficient, fixed-time decoding of images by utilizing a coarse-to-fine tree structure and parallel GPU prediction mechanisms.
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.
Community
Code will be added later. Enjoy reading !!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- The Invocation Bottleneck in LLM-Based Lossless Compression: What Can Be Removed and What Must Be Traded (2026)
- DCKV: Learned Transform Coding of the Prompt KV Cache in Hybrid Language Models (2026)
- WZIP and WLZ4: LZ77 Codecs with Match-Length-Dependent Sliding Windows (2026)
- Tetra: Serving Leech-Lattice Quantized LLMs at 2.7 Bits per Parameter (2026)
- TileShare: Training-Free Acceleration of Overlapping Tiled ViT Decoding (2026)
- WaveLLM: Wavelet-Domain LLM Entropy Modeling for Lossless Image Compression (2026)
- Cartesian Byte-Bank Models and Warp Lag Screening for GPU Lossless Compression (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.23108 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper