English

Towards 1000-fold Electron Microscopy Image Compression for Connectomics via VQ-VAE with Transformer Prior

Computer Vision and Pattern Recognition 2025-11-06 v2

Abstract

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.

Keywords

Cite

@article{arxiv.2511.00231,
  title  = {Towards 1000-fold Electron Microscopy Image Compression for Connectomics via VQ-VAE with Transformer Prior},
  author = {Fuming Yang and Yicong Li and Hanspeter Pfister and Jeff W. Lichtman and Yaron Meirovitch},
  journal= {arXiv preprint arXiv:2511.00231},
  year   = {2025}
}