3D Reconstruction in Noisy Agricultural Environments: A Bayesian Optimization Perspective for View Planning

TL;DR

This paper introduces a Bayesian optimization approach for view planning in 3D reconstruction within noisy agricultural environments, effectively handling environmental noise without requiring explicit noise models.

Contribution

It proposes a novel geometric-based quality function for view planning that accounts for environmental noise and an adaptive Bayesian optimization algorithm for improved 3D reconstruction.

Findings

Effective reconstruction with few cameras in noisy settings

Robustness of the method to environmental noise

Superior performance compared to traditional approaches

Abstract

3D reconstruction is a fundamental task in robotics that gained attention due to its major impact in a wide variety of practical settings, including agriculture, underwater, and urban environments. This task can be carried out via view planning (VP), which aims to optimally place a certain number of cameras in positions that maximize the visual information, improving the resulting 3D reconstruction. Nonetheless, in most real-world settings, existing environmental noise can significantly affect the performance of 3D reconstruction. To that end, this work advocates a novel geometric-based reconstruction quality function for VP, that accounts for the existing noise of the environment, without requiring its closed-form expression. With no analytic expression of the objective function, this work puts forth an adaptive Bayesian optimization algorithm for accurate 3D reconstruction in the presence of noise. Numerical tests on noisy agricultural environments showcase the merits of the proposed approach for 3D reconstruction with even a small number of available cameras.