CropCraft: Complete Structural Characterization of Crop Plants From Images

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.

Code and data availability

The paper describes a multi-view soybean/maize image dataset with manual LAI and leaf angle measurements and states it is available through the project page, but no public URL, repository, or code deposit is provided in the supplied blocks, and allowed_urls is empty, so no actionable paper-specific asset can be cited.

No evidence-backed public reproduction asset is currently recorded.