Evaluating Mesh Reconstruction Methods for Crop Phenotyping

Abstract

Phenotyping an agricultural crop is crucial for studying its entire life cycle, as it provides vital insights to improve yield and, ultimately, food production. Doing the same for crops grown on remote sites is a challenge for the specialists who cannot be available on-site. 3D reconstruction techniques offer a promising solution to this problem by enabling crop digitization, allowing specialists to access the resulting 3D crop models from anywhere at any time. In this work, we evaluate recent 3D reconstruction pipelines for crop phenotyping. We focus on 7 mesh reconstruction pipelines and measure the fidelity and consistency of their outputs qualitatively and quantitatively. Our results suggest that the meshes produced by the GGGS, PGSR, and 2DGS are preferable to the other pipelines, owing to their quantitative metrics and visually pleasing outputs. The GGGS pipeline is better than the second-best pipeline (2DGS) by about 27\% on the radar chart with 5 dimensions, namely, User ratings, Chamfer distance, LPIPS, PSNR, and SSIM.

Code and data availability

The paper announces a public release of its Cauliflower-13 dataset (RGB multi-view images of a cauliflower over 13 days), but no public URL, repository, or identifier is provided in the supplied blocks; the conclusion even calls it 'unreleased'. No author analysis code, models, or supplements with availability links or

No evidence-backed public reproduction asset is currently recorded.