Probabilistic Plant Modeling via Multi-View Image-to-Image Translation

TL;DR

This paper introduces a probabilistic method for reconstructing 3D plant branch structures from multi-view images, overcoming occlusion issues and providing a more accurate model than previous geometric approaches.

Contribution

It presents a novel Bayesian image-to-image translation framework for inferring hidden plant branches in 3D from multiple views.

Findings

Generated convincing 3D plant structures

Outperformed prior geometric methods

Demonstrated effectiveness in occluded regions

Abstract

This paper describes a method for inferring three-dimensional (3D) plant branch structures that are hidden under leaves from multi-view observations. Unlike previous geometric approaches that heavily rely on the visibility of the branches or use parametric branching models, our method makes statistical inferences of branch structures in a probabilistic framework. By inferring the probability of branch existence using a Bayesian extension of image-to-image translation applied to each of multi-view images, our method generates a probabilistic plant 3D model, which represents the 3D branching pattern that cannot be directly observed. Experiments demonstrate the usefulness of the proposed approach in generating convincing branch structures in comparison to prior approaches.