ViewSparsifier: Killing Redundancy in Multi-View Plant Phenotyping

Abstract

Plant phenotyping involves analyzing observable characteristics of plants to better understand their growth, health, and development. In the context of deep learning, this analysis is often approached through single-view classification or regression models. However, these methods often fail to capture all information required for accurate estimation of target phenotypic traits, which can adversely affect plant health assessment and harvest readiness prediction. To address this, the Growth Modelling (GroMo) Grand Challenge at ACM Multimedia 2025 provides a multi-view dataset featuring multiple plants and two tasks: Plant Age Prediction and Leaf Count Estimation. Each plant is photographed from multiple heights and angles, leading to significant overlap and redundancy in the captured information. To learn view-invariant embeddings, we incorporate 24 views, referred to as the selection vector, in a random selection. Our ViewSparsifier approach won both tasks. For further improvement and as a direction for future research, we also experimented with randomized view selection across all five height levels (120 views total), referred to as selection matrices.

Code and data availability

The paper describes the ViewSparsifier method and its use of the GroMo 2025 challenge dataset, but contains no availability statement, deposit, or public URL for the authors' own code, trained models, selection vectors, or derived data. The GroMo dataset and DINOv2 are cited third-party resources, not paper-specific释放s

No evidence-backed public reproduction asset is currently recorded.