AI Paper Atlas

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

PathDiff: Histopathology Image Synthesis with Unpaired Text and Mask Conditions

Mahesh Bhosale, Abdul Wasi, Yuanhao Zhai, Yunjie Tian, Samuel Border, Nan Xi, Pinaki Sarder, Junsong Yuan, David Doermann, Xuan Gong

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 9 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
jointly train on unpaired text and mask datasets (PathDiff) versus ControlNet for text-conditioned generationPathDiff · PathCap train (M2I PanNuke)CLIP-FID: 45.39 -> 18.52Improved
add PathDiff synthetic images to real training data for nucleus segmentationCellViT · PanNuke segmentationDice: 0.7834 -> 0.8164Improved
add PathDiff synthetic images to real training data for nucleus segmentationCellViT · CoNIC segmentationDice: 0.7927 -> 0.8356Improved
add SDM synthetic images to real training dataCellViT · MoNuSAC segmentationDice: 0.7089 -> 0.6783Hurt
train segmentation on PathDiff synthetic images only (ablation)CellViT · PanNuke segmentationDice: 0.7834 -> 0.7311Hurt
scale synthetic augmentation set beyond 2.5x real train size (ablation)PathDiff augmentation · PanNuke segmentationDice, F1No clear effect
use silver-standard masks instead of random text-mask pairing (ablation)PathDiff · PathCap (unified text+mask sampling)PLIP similarity: 22.09 -> 24.02Improved
set p_split to 0.5 rather than 0.2 or 0.8 for joint training (ablation)PathDiff · PanNuke test (mask-only)CLIP-FID: 7.88 / 8.97 -> 7.28Improved
set p_split to 0.5 rather than 0.2 for text-only generation (ablation)PathDiff · PathCap test (text-only)CLIP-FID: 15.74 -> 19.60Hurt
add instance edge mask channels to the conditioning mask (depth 3 -> 6) (ablation)PathDiff · PanNuke testCONCH FID: 102.37 -> 7.21Improved
fine-tune VAE on the target datasets (ablation)PathDiff VAE · VAE reconstructionFID: 6.94 -> 6.31Improved
use PathCap-fine-tuned U-Net checkpoint instead of TCGA-BRCA (ablation)PathDiff · PanNuke mask-to-imageCLIP-FID: 14.44 -> 7.21Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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