OneGrow: Unified Temporal Plant Image and Mask Generation
- 1ETHZ
Abstract
Image-based crop phenotyping benefits from image series that capture plant development together with organ-level labels. Such paired data are limited because organ annotation is expensive, and following the same plants over time requires repeated, registered imaging. Existing generative models for plants either synthesize temporal imagery without structural labels or generate labeled images without a temporal dimension. We introduce OneGrow, a latent flow-matching model that jointly models wheat images and their organ-segmentation masks over time. Images and masks share a single frozen image autoencoder. A reveal specifies which content is observed context, so the same model covers tasks such as mask-to-image synthesis, image-to-mask segmentation, and temporal forecasting. For sequences longer than the training window, a sliding-window roll-out generates each new image from the preceding frames, keeping long sequences temporally consistent. We train jointly on a large single-frame wheat dataset and a multi-year temporal dataset, using pseudo-labels from a pretrained segmentation model. We evaluate segmentation and image quality against held-out references and assess the multi-task and temporal behavior qualitatively.
Related
- Cross-modal alignment with language tokens for unified multilingual image-to-text generation.
- A unified decision framework combines phenotypic and genomic information for nonlinear selection in plant breeding
- UniHAR: A unified hierarchical transformer with multi-scale temporal modeling for wearable human activity recognition
- A context-aware temporal modeling through unified multi-scale temporal encoding and hierarchical sequence learning for single-channel EEG sleep staging
- Limits to Plant Species' Ranges: A Unified Eco-Evolutionary Model and Molecular Mechanisms.
BibTeX
@misc{boss2026onegrow,
title = {{OneGrow: Unified Temporal Plant Image and Mask Generation}},
author = {M. Boss and M. Volpi and L. Roth},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.11.750899},
url = {https://www.biorxiv.org/content/10.64898/2026.09.11.750899v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - OneGrow: Unified Temporal Plant Image and Mask Generation
AU - M. Boss
AU - M. Volpi
AU - L. Roth
PY - 2026
DA - 2026/09/11
PB - bioRxiv
DO - 10.64898/2026.09.11.750899
UR - https://www.biorxiv.org/content/10.64898/2026.09.11.750899v1
AB - Image-based crop phenotyping benefits from image series that capture plant development together with organ-level labels. Such paired data are limited because organ annotation is expensive, and following the same plants over time requires repeated, registered imaging. Existing generative models for plants either synthesize temporal imagery without structural labels or generate labeled images without a temporal dimension. We introduce OneGrow, a latent flow-matching model that jointly models wheat images and their organ-segmentation masks over time. Images and masks share a single frozen image autoencoder. A reveal specifies which content is observed context, so the same model covers tasks such as mask-to-image synthesis, image-to-mask segmentation, and temporal forecasting. For sequences longer than the training window, a sliding-window roll-out generates each new image from the preceding frames, keeping long sequences temporally consistent. We train jointly on a large single-frame wheat dataset and a multi-year temporal dataset, using pseudo-labels from a pretrained segmentation model. We evaluate segmentation and image quality against held-out references and assess the multi-task and temporal behavior qualitatively.
ER -