BigCell: Generating Gigapixel Whole-Slide Images

Srikar Yellapragada; Alexandros Graikos; Zilinghan Li; Kostas Triaridis; Tarak Nath Nandi; Ji Dong K Bai; Beatrice Knudsen; Tahsin Kurc

cs.CVOct 9, 2026

BigCell: Generating Gigapixel Whole-Slide Images

Authors: Srikar Yellapragada, Alexandros Graikos, Zilinghan Li, Kostas Triaridis, Tarak Nath Nandi, Ji Dong K Bai, Beatrice Knudsen, Tahsin Kurc,

Organizations: Stony Brook University · Argonne National Laboratory · University of Chicago · The University of Utah ·

Abstract

Whole-slide images (WSIs) are gigapixel-scale digital scans of histopathology tissue and serve as the primary basis for cancer diagnosis. Existing histopathology generative models operate at the patch scale, producing fixed-size tiles of at most 1024 $\times$ 1024 pixels which encompass only a small fraction of the WSI. In contrast, text reports for clinical diagnoses and slide-level diagnostic labels -- the supervision that exists at scale -- operate at the whole-slide level. We present BigCell, the first approach to generate coherent whole-slide histopathology images at native gigapixel resolution. BigCell trains a flow-matching transformer at 2048 $\times$ 2048 pixels on over 120,000 publicly available WSIs spanning multiple organ types. Conditioning on embeddings from pathology foundation models and using an inference-time sliding-window pipeline, BigCell generates coherent images of up to 32,768 $\times$ 32,768 pixels, outperforming prior tile generators on both tile-level and slide-level fidelity metrics. To make gigapixel synthesis practical, we introduce an adaptive scheduling strategy that prioritizes important slide regions, speeding up image generation by over 3\ttimes with minimal quality degradation. Furthermore, we propose the first text-to-image synthesis at 8k resolution by training a separate model that produces dense conditioning grids directly from pathology text reports. We demonstrate that augmenting with synthetic samples improves slide-level few-shot classification performance by up to $18 \%$ over baselines trained on real data.

Figures & tables

Figure 1: We present synthetic images generated using BigCell. Left: 32768 $\times$ 32768 images along with 2048 $\times$ 2048 crops, highlighting the realism achieved both at the macro-scale and cellular detail level. Right: Two 8192 $\times$ 8192 images per report generated from text. Best viewed zoomed in.

Figure 2: Overview of the BigCell pipeline. (a) We obtain a dense grid of conditioning embeddings either from a reference WSI or sampled using a model conditioned on text (CGM). This serves as the controllable blueprint that defines the large-scale structures of the whole-slide image. (b) The tile generator uses the local conditioning to predict how to transform the slide locally. (c) Using the tile generator on overlapping windows, we aggregate the per-window velocities into a global velocity field and iteratively denoise the noisy slide into a gigapixel image, allowing us to efficiently synthesize WSIs without explicitly training on their scale.

	Slide-level Similarity		Patch-level Similarity				Fréchet Distance
Generator	TITAN↑	MOOZY↑	V2 mean ↑	V2 5th ↑	H1 mean ↑	H1 5th ↑	V2 FD ↓	H1 FD ↓
PixCell	. 941	. 900	. 778	. 632	. 667	. 509	1023	696
CytoSyn	.929	.864	.753	.502	.640	.457	895	604
MuPaD	.646	.755	.462	.258	.342	.196	981	641
LRDM	.531	.693	.513	.334	.395	.247	731	502
ZoomLDM	.708	.801	.646	.464	.477	.325	8 15	5 53

Table 1: Comparison at 8192

\times

8192 resolution. V2: Virchow-2; H1: H-Optimus-1; FD: Fréchet distance (no test). ∗ :

p<0.001

, two-sided paired Wilcoxon vs. best baseline (

N=100

). Resolution- and data-matched comparisons are in Appendix E.2 .

Generator	Same organ↑	Same diagnosis↑	All three fields↑
PixCell	6 3%	4 2%	3 8%
CytoSyn	54%	26%	25%
MuPaD	41%	17%	17%
ZoomLDM	61%	40%	36%
LRDM	59%	31%	30%
BigCell	69%	46%	41%

Table 2: Report-level agreement at 8192

\times

8192 resolution (

N=100

, same ROIs as Table 1 ): fraction of generated/reference pairs whose MedGemma-4B reports agree on the tissue of origin, the diagnosis, and all three fields (organ, malignancy, diagnosis).

Figure 3: Adaptive window scheduling compared with simple, fewer-step sampling and the full 38440 NFE baseline at 32k resolution (N=256), evaluated at

r\in\{0.05,0.09,0.25,0.41\}

. At

r=0.25

, we obtain a 3.1

\times

speedup (15.6 h

\rightarrow

4.97 h on a single Intel Data Center GPU Max 1550).

Method	Sim	Recall@1	Recall@5	Sim	Recall@1	Recall@5
	TITAN			PRISM
Real data (paired)	0.551	0.211	0.655	0.499	0.148	0.430
BigCell	0.487	0.169	0.655	0.454	0.106	0.387

Table 3: TITAN and PRISM CLIP-style similarity and report-to-image retrieval recall on 150 held-out reports. CGM-generated images approach the alignment of real data under both encoders.

Figure 5: Synthetic 8192 $\times$ 8192 image generated by BigCell from a pathology text report, showing extensive pancreatic ductal adenocarcinoma.

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Step	Tensor	2048 $\times$ 2048 tile	32,768 $\times$ 32,768 canvas
Input / output image	image $x$	$2048\times 2048\times 3$	$32768\times 32768\times 3$
VAE encode / decode	latent $z$	$256\times 256\times 32$	$4096\times 4096\times 32$
UNI-2 on 256 $\times$ 256 patches	conditioning grid $y$	$8\times 8\times 1536$	$128\times 128\times 1536$
Denoising (per window)	velocity $v_{\theta}(z_{t},t,y)$	$256\times 256\times 32$	$256\times 256\times 32$

Appendix

Table 5: Tensor shapes in BigCell for a single 2048

\times

2048 tile and a 32,768

\times

32,768 canvas. At 32k, each sliding window operates on a

256\times 256\times 32

latent region with the corresponding

8\times 8\times 1536

slice of the conditioning grid.

Resolution	Batch size	Conditioning	lr	t schedule
256	4800	$1\times 1536$	2e-4	Uniform
512	2400	$4\times 1536$	1e-4	Uniform
1024	720	$16\times 1536$	1e-4	Shifted, $\alpha=3$
2048	360	$64\times 1536$	1e-4	Shifted, $\alpha=3$

Appendix

Table 6: Progressive training schedule for BigCell tile . We train for one epoch at each resolution, and initialize the model from the previous stage weights.

Component	BigCell tile	CGM
Optimizer	AdamW	AdamW
$\beta_{1},\beta_{2}$	0.9, 0.999	0.9, 0.95
Weight decay	0	0
EMA decay	0.9999	0.9995
Gradient clipping	1.0	1.0
Warmup	5,000 steps (linear)	40 epochs (linear)

Appendix

Table 7: Training configuration for BigCell tile and CGM

Resolution	Batch size	Sec/Iter	Compute/Sample
1024	720	1.35	1.0 $\times$
2048	360	5.59	8.3 $\times$
4096	360	65	96 $\times$

Appendix

Table 8: Training cost across native resolutions, measured on the Intel GPU cluster. Cost scales quadratically, making training at 4096 impractical. The 4096 row is a single-iteration benchmark; we did not train a model at this resolution.

Figure 6: Effect of tile generator’s native resolution on 8192

\times

8192 generation quality. Both slide-level and tile-level metrics improve with resolution, with diminishing returns beyond 1024.

	Slide-level Similarity		Patch-level Similarity		Fréchet Distance
Generator	TITAN↑	MOOZY↑	V2 mean ↑	H1 mean ↑	V2 FD ↓	H1 FD ↓
Matched native resolution
PixCell-1024	.941	.900	.778	.667	1023	696
BigCell-1024	.952	.971	.849	.723	912	617
Matched native resolution, data, and compute
BigCell-summarizer-2048	.926	.868	.627	.505	1229	813

Appendix

Table 9: Resolution-matched comparisons at 8192

\times

8192 resolution (

N=100

, same ROIs as Table 1 ). Top: BigCell and PixCell at the same 1024 native resolution. Bottom: BigCell against a model with identical backbone, data, sampler, and training budget that uses ZoomLDM’s summarizer-based conditioning.

Figure 7: Effect of window selection strategy on 8192

\times

8192 generation quality. Our CFG importance-based strategy outperforms random selection across all metrics.

Field agreement	BigCell vs. reference	Chance
Same tissue of origin	85.9% [81.1, 89.6]	9.1% [7.7, 10.7]
Same diagnosis	72.2% [66.4, 77.3]	9.2% [7.4, 11.1]
All three fields identical	71.0% [65.1, 76.2]	6.0% [4.6, 7.7]

Appendix

Table 10: Report-level agreement at 32,768

\times

32,768 resolution (

N=256

, full compute). Chance is the rate at which a real report matches the synthetic report of a different slide, averaged over all such pairings. 95% Wilson intervals in brackets.

Figure 8: Pathologist evaluation interface. Each trial shows an 8192 $\times$ 8192 image (real or synthetic) and four candidate reports (one of which is true). Pathologists indicate matching report(s) and classify the image as real or synthetic.

Figure 9: Qualitative comparison of 8192 $\times$ 8192 generation between BigCell tile and baselines. Top row: full 8k image. Bottom row: 2k crop from the boxed region.

Figure 10: Visualization of CFG-magnitude importance scores on two synthetic 8192 $\times$ 8192 images. Tissue regions receive high importance, while background regions receive low importance.

Figure 11: 32,768 $\times$ 32,768 pixel breast tissue image generated by BigCell (top), with progressive zoom-in crops from the marked regions (bottom).

Figure 12: 32,768 $\times$ 32,768 pixel lung tissue image generated by BigCell (top), with progressive zoom-in crops from the marked regions (bottom).

Figure 13: 32,768 $\times$ 32,768 pixel mesothelial tissue image generated by BigCell (top), with progressive zoom-in crops from the marked regions (bottom).

Image Generation

Image generation studies models that create or edit images from text, examples, layouts, and other structured controls.

See all 461 papers

From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology
Aug 4, 2026Basit Alawode, Moshira Ali Abdalla, Dwarikanath Mahapatra +2Representation Learning Vision Transformer
Khalifa University of Science and Technology, UAE · University of Western Australia, Australia
MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding
Mar 24, 2026Basit Alawode, Arif Mahmood, Muaz Khalifa Al-Radi +6Whole-Slide Image Analysis Medical VLMs
Department of Computer Science, Khalifa University of Science and Technology, UAE. · Information Technology University, Pakistan. · KAU, KSA. +1
SlideMix: Enhancing Whole Slide Image Analysis via Multimodal Shuffling
Aug 31, 2026Chad Wong, Sicheng Chen, Tianyi Zhang +4Data Augmentation Histopathology Image Classification
1Nhu Department of Electrical Engineering and Computer Science, University of California, Irvine · Department of Electrical & Computer Engineering, National University of Singapore · 3PuzzleLogic Pte Ltd, Singapore 229594, Singapore

Aug 4, 2026J/K move · Enter open · S save

From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology

Basit Alawode, Moshira Ali Abdalla, Dwarikanath Mahapatra, Muzammal Naseer+1

Khalifa University of Science and Technology, UAE · University of Western Australia, Australia

Representation Learning Vision Transformer Pathology Foundation Models Histopathology Image Classification Whole-Slide Image Analysis

Open paper AskPDF arXiv

Vision Transformers (ViTs) and their hierarchical variants have achieved strong performance in Computational Pathology (CPath). However, most are pre-trained on single-resolution Whole Slide Images (WSIs), limiting their generalization across arbitrary resolutions. Gigapixel WSIs inherently contain diagnostic patterns at multiple scales, including cellular morphologies, tissue architectures, and global context, mirroring how expert pathologists examine WSIs. We introduce Multi-Resolution Pyramid Transformer (MRPT), a model that hierarchically aggregates multi-resolution information from cellular to tissue and WSI levels. MRPT employs a biologically meaningful Consecutive Cross-Resolution Attention (CCRA) mechanism to capture scale-independent interactions and enforces multi-resolution semantic consistency by aligning embeddings across resolutions, yielding robust and generalizable WSI representations. Pre-trained in a multi-resolution self-supervised manner on 624M patches, 2.4M regions, and 36K WSIs, MRPT learns rich coarse-to-fine histopathology features. Extensive experiments on 34 diverse datasets show that MRPT surpasses recent foundation models and Multimodal Large Language Models (MLLMs) in cancer subtype classification, tissue phenotyping, and Visual Question Answering (VQA) for WSI understanding.

Abstract

Image Generation

Explore similar work

From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology

MLLM-HWSI: A Multimodal Large Language Model for Hierarchical Whole Slide Image Understanding

SlideMix: Enhancing Whole Slide Image Analysis via Multimodal Shuffling