CropCraft: Complete Structural Characterization of Crop Plants From Images

TL;DR

This paper introduces a novel method for 3D modeling of crop plants from images, overcoming occlusion and complex geometry challenges to produce complete, biologically plausible models for agricultural applications.

Contribution

It presents an inverse procedural modeling approach that estimates plant morphology from images using neural radiance fields and specialized loss functions.

Findings

The method produces complete 3D crop models from real images.

Reconstructed models are biologically plausible and useful for monitoring.

Demonstrated applications in agricultural monitoring and simulation.

Abstract

The ability to automatically build 3D digital twins of plants from images has countless applications in agriculture, environmental science, robotics, and other fields. However, current 3D reconstruction methods fail to recover complete shapes of plants due to heavy occlusion and complex geometries. In this work, we present a novel method for 3D modeling of agricultural crops based on optimizing a parametric model of plant morphology via inverse procedural modeling. Our method first estimates depth maps by fitting a neural radiance field and then optimizes a specialized loss to estimate morphological parameters that result in consistent depth renderings. The resulting 3D model is complete and biologically plausible. We validate our method on a dataset of real images of agricultural fields, and demonstrate that the reconstructed canopies can be used for a variety of monitoring and simulation applications.