GrowFields: Compositional 4D Neural Fields for Topology-Changing Plant Growth

2026-07-03

AI Summary

This work addresses the challenges of modeling plant growth from sparse longitudinal 3D observations, where organ topology changes, non-rigid deformations, and the absence of explicit temporal correspondences pose significant difficulties. To overcome these issues, the authors propose a compositional dynamic neural field approach that decomposes the plant into individual organs, each modeled in its own canonical coordinate system. A shared continuous neural deformation field, coupled with learnable implicit organ codes, jointly optimizes the full 4D growth process. This framework uniquely enables a unified representation of asynchronous organ development and topological changes without requiring explicit temporal alignment, while preserving both geometric accuracy and organ identity awareness. Evaluated on four plant datasets, the method substantially outperforms existing approaches in spatial precision, temporal consistency, and morphological fidelity.

Abstract

Quantifying plant growth dynamics from sparse longitudinal 3D observations is fundamental for agriculture and plant sciences. Yet, plants pose unique challenges: they undergo intricate non-rigid deformations, exhibit changing topology as new organs emerge, and often lack explicit temporal correspondences between consecutive data acquisitions due to newly formed tissue. Methods designed for general scenes struggle to model topology changes and asynchronous organ growth characteristic of plants. To address these challenges, we introduce GrowFields, a compositional dynamic neural field representation for organ-aware 4D plant growth modelling from point cloud time series. Our approach decomposes a plant into its constituent organs and aligns each organ into its own canonical coordinate frame, isolating intrinsic growth patterns from global plant motion. We then learn a shared continuous neural deformation field that models temporal dynamics across all organs, conditioned on learnable per-organ latent codes capturing organ identity and growth characteristics. The resulting modular yet unified representation naturally accommodates the asynchronous development of plant organs while remaining grounded in the practical setting of organ-level plant tracking. We evaluate GrowFields on growth sequences from four plant species, assessing geometric fitting and organ tracking accuracy using manually annotated leaf-tip trajectories. Results demonstrate consistent improvements in spatial precision, temporal coherence, and morphological fidelity over a range of existing representations.

Problem

• plant growth
• topology change
• 4D modeling
• organ tracking
• sparse observations

Innovation

• compositional neural fields
• 4D plant growth modeling
• topology-changing dynamics
• organ-aware representation
• neural deformation field