m 7.74 to 3.91 and mean leaf-count MAE from 5.52 to 3.08 compared to the GroMo baseline, corresponding to improvements of 49.5% and 44.2%, respectively. The unified formulation simplifies the pipeline by replacing the conventional dual-model setup while improving robustness to missing views. The modela and code is available at: https://github.com/SimonWarmers/CLIP-MVP Index Terms: Plant phenotyping, Multi-view learning, Multi-task regression, Precision agriculture † † address: † Computer Vision Lab, CAIDAS, IFI, University of Würzburg, Germany ‡ Technological University Dublin, Ireland 1 Introduction Plant phenotyping from multiview imagery is crucial for precision agriculture, enabling non-
Open resource ↗SimonWarmers/CLIP-MVP · lines:1-53Unverified paper record
CLIP-Guided Multi-Task Regression for Multi-View Plant Phenotyping
arXiv (Cornell University) · 4 Mar 2026 · 10.48550/arxiv.2603.04091
Abstract
Modeling plant growth dynamics plays a central role in modern agricultural research. However, learning robust predictors from multi-view plant imagery remains challenging due to strong viewpoint redundancy and viewpoint-dependent appearance changes. We propose a level-aware vision language framework that jointly predicts plant age and leaf count using a single multi-task model built on CLIP embeddings. Our method aggregates rotational views into angle-invariant representations and conditions visual features on lightweight text priors encoding viewpoint level for stable prediction under incomplete or unordered inputs. On the GroMo25 benchmark, our approach reduces mean age MAE from 7.74 to 3.91 and mean leaf-count MAE from 5.52 to 3.08 compared to the GroMo baseline, corresponding to improvements of 49.5% and 44.2%, respectively. The unified formulation simplifies the pipeline by replacing the conventional dual-model setup while improving robustness to missing views. The models and code is available at: https://github.com/SimonWarmers/CLIP-MVP
Plant phenotyping relevance
植物画像から葉数・植物齢を推定するマルチビュー表現学習手法を開発し、ベンチマークで性能評価しており、表現型取得・推定が研究の中心である。
abstractWe propose a level-aware vision language framework that jointly predicts plant age and leaf count using a single multi-task model built on CLIP embeddings.
abstractOn the GroMo25 benchmark, our approach reduces mean age MAE from 7.74 to 3.91 and mean leaf-count MAE from 5.52 to 3.08 compared to the GroMo baseline
Code and data availability
The paper explicitly states that the model and code are publicly available at the authors' GitHub repository, which qualifies as a paper-specific public code asset.
This is an automatically classified, unverified record. Curator approval is required before any resource enters the Catalog.