跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 6 天前AI 評分47

FMT:固定並行步數下的無損圖像壓縮

FMT: Lossless Image Compression in a Fixed Number of Parallel Steps

AI 導讀

FMT 無損圖像格式以由粗至細的樹狀結構及 GPU 並行預測,讓任何尺寸的圖像都能在固定數目的順序步驟內解碼。使用大型網絡時,FMT 在同一 A100 上解碼 Kodak 相片,比測試中的 learned codecs 快 9 至 61 倍,檔案大小相同或更小。不使用網絡時,FMT 在檔案大小和速度上均勝過 NVIDIA 的 HTJ2K。

正文

Published on Nov 17

Authors:

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.

View arXiv page View PDF Add to collection

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

Cite arxiv.org/abs/2611.23108 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.23108 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.23108 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co