Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.00231 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911249951883264 |
|---|---|
| author | Yang, Fuming Li, Yicong Pfister, Hanspeter Lichtman, Jeff W. Meirovitch, Yaron |
| author_facet | Yang, Fuming Li, Yicong Pfister, Hanspeter Lichtman, Jeff W. Meirovitch, Yaron |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00231 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards 1000-fold Electron Microscopy Image Compression for Connectomics via VQ-VAE with Transformer Prior Yang, Fuming Li, Yicong Pfister, Hanspeter Lichtman, Jeff W. Meirovitch, Yaron Computer Vision and Pattern Recognition 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. |
| title | Towards 1000-fold Electron Microscopy Image Compression for Connectomics via VQ-VAE with Transformer Prior |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.00231 |