Baltic: A benchmark and cross-domain strategy for 3D reconstruction across air and underwater domains under varying illumination
The International Journal of Robotics Research · 26.10.2026
DOI: 10.1177/02783649261494624 ↗Kurz gefasst
Fachartikel in der Zeitschrift The International Journal of Robotics Research, online erschienen am 26.10.2026. Verfasst von Michele Grimaldi und 5 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EPSRC project UNderwater IntervenTion for offshore renewable Energies.
Abstract (Originalsprache)
Robust 3D reconstruction across varying environmental conditions remains a critical challenge for robotic perception, particularly when transitioning between air and water. To address this, we introduce BALTIC, a controlled benchmark designed to systematically evaluate modern 3D reconstruction methods under variations in medium and lighting. The benchmark comprises 13 datasets spanning two media (air and water) and three lighting conditions (directional, artificial, and mixed), with additional variations in motion type, scanning pattern, and initialization trajectory, resulting in a diverse set of sequences. Our experimental setup features a custom water tank equipped with a monocular camera and an HTC Vive tracker, enabling accurate ground-truth pose estimation. We further investigate cross-domain reconstruction by augmenting underwater image sequences with a small number of in-air views captured under similar lighting conditions. We evaluate Structure-from-Motion reconstruction using COLMAP in terms of both trajectory accuracy and scene geometry, and use these reconstructions as input to Neural Radiance Fields and 3D Gaussian Splatting methods. The resulting models are assessed against ground-truth trajectories and in-air references, while rendered outputs are compared using perceptual and photometric metrics. Additionally, we perform a color restoration analysis to evaluate radiometric consistency across domains. Our results show that under controlled, texture-consistent conditions, Gaussian Splatting with simple preprocessing (e.g., white balance correction) can achieve performance comparable to specialized underwater methods, although its robustness decreases in more complex and heterogeneous real-world environments.
Förderung
- EPSRC project UNderwater IntervenTion for offshore renewable Energies
Zitieren
APA
Grimaldi, M., Nakath, D., Pizarro, O., Willners, J. S., Carlucho, I., & Petillot, Y. R. (2026). Baltic: A benchmark and cross-domain strategy for 3D reconstruction across air and underwater domains under varying illumination. The International Journal of Robotics Research. https://doi.org/10.1177/02783649261494624
Vancouver
Grimaldi M, Nakath D, Pizarro O, Willners JS, Carlucho I, Petillot YR. Baltic: A benchmark and cross-domain strategy for 3D reconstruction across air and underwater domains under varying illumination. The International Journal of Robotics Research. 2026. doi:10.1177/02783649261494624
BibTeX
@article{Grimaldi2026,
author = {Grimaldi, Michele and Nakath, David and Pizarro, Oscar and Willners, Jonatan Scharff and Carlucho, Ignacio and Petillot, Yvan R.},
title = {Baltic: A benchmark and cross-domain strategy for 3D reconstruction across air and underwater domains under varying illumination},
journal = {The International Journal of Robotics Research},
year = {2026},
doi = {10.1177/02783649261494624}
}
EUVIMED