AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

EM3M: An Electron Micrograph Dataset for Microstructural Segmentation and Generation

Nan Wang, Zhiyi Xia, Yiming Li, Shi Tang, Zoe Fan, Xi Fang, Haoyi Tao, ZHANG SIYUAN, Guolin Ke, Yanhui Hong

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add 30K generated images to real training data (ablation)UniAIMS trained on 4K real · EM3M (full test set)mAP@0.5: 0.800 -> 0.809Improved
add 30K generated images to real training data (ablation)UniAIMS trained on 4K real · EM3M (full test set)PQ@0.5: 0.704 -> 0.707Improved
increase real training data from 1K to 4K images (ablation)UniAIMS · EM3M (full test set)mAP@0.5: 0.767 -> 0.800Improved
increase generated training data from 5K to 30K images (ablation)UniAIMS · EM3M (full test set)mAP@0.5: 0.760 -> 0.791Improved
replace 3K real images by 30K generated images (ablation)UniAIMS · EM3M (full test set)mAP@0.5: 0.795 (3K real) vs 0.791 (30K generated)No clear effect
pretrain on 30K generated images instead of SA1B (ablation)UniAIMS · EM3M (full test set)mAP@0.5Improved
finetune on external dataset after zero-shotUniAIMS · Okunev (external)mAP: 0.81 -> 0.84Improved
finetune on external dataset after zero-shotUniAIMS · EMPS (external)mAP: 0.89 -> 0.92Improved
finetune SDXL with LoRA on EM3M structured promptsSDXL · Generated vs real EMFID: 213.16 -> 34.03Improved
finetune SDXL with LoRA on EM3M structured promptsSDXL · Generated vs real EMStyle similarity: 0.669 -> 0.958Improved
use flow-based UniAIMS (no size model, LSJ augmentation, modern backbone) instead of CellposeCellpose · EM3M (sparse subset, <100 instances)mAP@0.5: 0.650 -> 0.818Improved
use UniAIMS instead of CellposeCellpose · EM3M (full test set)mAP@0.5: 0.711 -> 0.800Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy