Why 3D Reconstruction Breaks Down on Under-Ice AUV Video, and How to Predict It

Abstract:Reconstruction of 3D structures using under-ice AUV video footage has been inaccurate, although it is not certain whether this is due to shortcomings in the methods or an inherent deficiency of the capture system. We test four different models for reconstruction on the same Antarctic under-ice AUV video (Icefin, Kamb Ice Stream): classical feature matching SfM, differentiable photometric splatting, volumetric depth fusion, and a pose-free feed-forward foundation model. All four fail, each in a distinct way: near-total registration yielding almost no structure, geometrically broken output despite healthy photometric metrics, a persistent coverage artifact, and unstable cross-chunk scale. We show that all four are consistent with the same capture regime, a small camera-baseline-to-scene-depth ratio. Following our analysis, we propose a detection system that flags this type of failure in minutes, rather than hours of wasted compute.

Short paper presented at the 2nd Workshop on Marine Vision, ECCV 2026, Malmö, Sweden, September 8, 2026. Published on OpenReview: this https URL

Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)

arXiv:2610.19993 [cs.CV]

(or arXiv:2610.19993v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2610.19993 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.