GrowFields: Compositional 4D Neural Fields for Topology-Changing Plant Growth
2026-07-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present GrowFields, a method to track how plants grow over time using 3D scans taken at different moments. Since plants change shape, grow new parts, and don’t always have clear time connections between scans, the authors break each plant into parts (like leaves) and study each separately in its own space. They use a special neural network that learns how each part changes and grows, helping to handle parts growing at different times. Tested on multiple plant species, their method shows better accuracy in tracking plant growth and shapes compared to other approaches.
3D point cloudneural deformation fieldtopology changesorgan-level trackingplant growth dynamicslatent codesnon-rigid deformationtemporal coherencemorphological fidelitycontinuous neural representation
Authors
Joaquin Gajardo, Michele Volpi, Marko Mihajlovic, Siyu Tang, Lukas Roth, Sergey Prokudin
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.