AI Pulse
📄 论文解读

学出来的压缩更小,却慢得没人用

学出来的无损压缩能把照片压得更小,可我们存档、训练用的还是老式编码——因为解码一张图,学出来的要几秒,老式的只要几毫秒。这篇的观察是:那几秒大半花在「等」上,不在「算」上:网络要等它依赖的像素先出来,熵解码器又一个一个地读。他们把解码顺序和熵编码器一起设计,把图存成一棵由粗到细的树,同一层的值互不依赖,GPU 一次预测一整层,并行的 rANS 通道带着状态逐层往下走,于是不管图多大,顺序步骤数都是固定的。同一块 A100 上,他们跑过的编码器没有一个能在体积和速度上同时赢过它;不带网络的那档就比 NVIDIA 的 HTJ2K 又小又快,带大网络的解码 Kodak 照片比学出来的快 9 到 61 倍,体积还不更大。它不是你明天能装上的东西——要变成你相册和模型训练集里的默认格式,还得看生态愿不愿意换。

📄 原文摘要(英文)

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.

arXiv 原文

订阅 AI Pulse

每天 08:00 · 12:30 · 18:30 · 23:50 更新