Model-based metric 3d shape and motion reconstruction of wild bottlenose dolphins in drone-shot videos
Authored by Daniele Baieri, Riccardo Cicciarella, Michael Krützen, Emanuele Rodolà, Silvia Zuffi
Published in International Journal of Computer Vision (IJCV) 2026
Abstract
We address the problem of estimating the metric 3D shape and motion of wild dolphins from monocular video captured with a drone in a natural setting, with the aim of assessing their body condition. While considerable progress has been made in reconstructing 3D models of terrestrial quadrupeds, aquatic animals remain unexplored due to the difficulty of observing them in their natural underwater environment. To address this, we propose a model-based approach that incorporates a transmission model to account for water-induced occlusion. We apply our method to video captured under different sea conditions. We estimate mass and volume, and compare our results to a manual 2D measurements-based method. Additionally, we apply our method to video of captive animals with known ground truth mass. While in our experiments the manual approach is often more accurate, our method demonstrates a distinct advantage when applied to larger specimen. These findings highlight the potential of our method as a scalable and automated alternative for mass and volume estimation of dolphins from monocular video.
Resources
Bibtex
@inproceedings{ baieri2026dolphins,
author = { Daniele Baieri and Riccardo Cicciarella and Michael Krützen and Emanuele Rodolà and Silvia Zuffi },
title = { Model-based metric 3d shape and motion reconstruction of wild bottlenose dolphins in drone-shot videos },
booktitle = { International Journal of Computer Vision (IJCV) },
year = { 2026 },
}