Saved in:
Bibliographic Details
Main Authors: Xiang, Shuai, Guo, Wei, Burridge, James, Liu, Shouyang, Lu, Hao, Fukatsu, Tokihiro
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.27519
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914429865558016
author Xiang, Shuai
Guo, Wei
Burridge, James
Liu, Shouyang
Lu, Hao
Fukatsu, Tokihiro
author_facet Xiang, Shuai
Guo, Wei
Burridge, James
Liu, Shouyang
Lu, Hao
Fukatsu, Tokihiro
contents Vision Foundation Models (VFM) pre-trained on large-scale unlabeled data have achieved remarkable success on general computer vision tasks, yet typically suffer from significant domain gaps when applied to agriculture. In this context, we introduce $SPROUT$ ($S$calable $P$lant $R$epresentation model via $O$pen-field $U$nsupervised $T$raining), a multi-crop, multi-task agricultural foundation model trained via diffusion denoising. SPROUT leverages a VAE-free Pixel-space Diffusion Transformer to learn rich, structure-aware representations through denoising and enabling efficient end-to-end training. We pre-train SPROUT on a curated dataset of 2.6 million high-quality agricultural images spanning diverse crops, growth stages, and environments. Extensive experiments demonstrate that SPROUT consistently outperforms state-of-the-art web-pretrained and agricultural foundation models across a wide range of downstream tasks, while requiring substantially lower pre-training cost. The code and model are available at https://github.com/UTokyo-FieldPhenomics-Lab/SPROUT.
format Preprint
id arxiv_https___arxiv_org_abs_2603_27519
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SPROUT: A Scalable Diffusion Foundation Model for Agricultural Vision
Xiang, Shuai
Guo, Wei
Burridge, James
Liu, Shouyang
Lu, Hao
Fukatsu, Tokihiro
Computer Vision and Pattern Recognition
Vision Foundation Models (VFM) pre-trained on large-scale unlabeled data have achieved remarkable success on general computer vision tasks, yet typically suffer from significant domain gaps when applied to agriculture. In this context, we introduce $SPROUT$ ($S$calable $P$lant $R$epresentation model via $O$pen-field $U$nsupervised $T$raining), a multi-crop, multi-task agricultural foundation model trained via diffusion denoising. SPROUT leverages a VAE-free Pixel-space Diffusion Transformer to learn rich, structure-aware representations through denoising and enabling efficient end-to-end training. We pre-train SPROUT on a curated dataset of 2.6 million high-quality agricultural images spanning diverse crops, growth stages, and environments. Extensive experiments demonstrate that SPROUT consistently outperforms state-of-the-art web-pretrained and agricultural foundation models across a wide range of downstream tasks, while requiring substantially lower pre-training cost. The code and model are available at https://github.com/UTokyo-FieldPhenomics-Lab/SPROUT.
title SPROUT: A Scalable Diffusion Foundation Model for Agricultural Vision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.27519