New neural field model captures plant growth dynamics and topology changes

Researchers have developed GrowFields, a novel compositional dynamic neural field representation designed to model the complex growth patterns of plants. This method decomposes plants into individual organs, aligning each into its own coordinate frame to isolate intrinsic growth from global motion. By learning a shared continuous neural deformation field conditioned on organ-specific latent codes, GrowFields can naturally accommodate asynchronous organ development and changing topology. Evaluations on four plant species demonstrated improved spatial precision, temporal coherence, and morphological fidelity compared to existing representations. AI

IMPACT This new neural field representation could advance agricultural science by enabling more accurate tracking and modeling of plant development.

RANK_REASON The cluster contains a research paper detailing a new method for modeling plant growth using neural fields. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• Gotit.pub
• GrowFields
• Hugging Face
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →