Petascale electron microscopy (EM) datasets push storage, transfer, and downstream analysis toward their current limits. We present a vector-quantized variational autoencoder-based (VQ-VAE) compression framework for EM that spans 16x to 1024x and enables pay-as-you-decode usage: top-only decoding for extreme compression, with an optional Transformer prior that predicts bottom tokens (without changing the compression ratio) to restore texture via feature-wise linear modulation (FiLM) and concatenation; we further introduce an ROI-driven workflow that performs selective high-resolution reconstruction from 1024x-compressed latents only where needed.

翻译：拍字节级别的电子显微镜（EM）数据集将存储、传输及下游分析推向当前技术极限。我们提出一种基于矢量量化变分自编码器（VQ-VAE）的EM压缩框架，支持16倍至1024倍压缩比，并实现按需解码功能：通过仅解码顶层实现极限压缩，同时可选采用Transformer先验模型（在不改变压缩率的前提下）预测底层标记，借助特征线性调制（FiLM）与拼接操作恢复纹理细节；我们进一步引入兴趣区域驱动的工作流程，能够从1024倍压缩的潜在表示中，仅在需要区域执行选择性高分辨率重建。