Saved in:
| Main Authors: | , , , , , |
|---|---|
| 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 |