Leveraging 6DoF Pose Foundation Models For Mapping Marine Sediment Burial

TL;DR

This paper presents PoseIDON, a computer vision pipeline that combines deep foundation models with multiview photogrammetry to accurately estimate the burial depth and pose of objects on the seafloor from ROV footage, aiding environmental assessment.

Contribution

It introduces a novel method that integrates deep learning features with multiview geometry to estimate 6DoF pose and burial depth of seafloor objects from remote imagery.

Findings

Mean burial depth error of ~10 cm

Successfully mapped spatial burial patterns

Validated on 54 objects at a dumpsite

Abstract

The burial state of anthropogenic objects on the seafloor provides insight into localized sedimentation dynamics and is also critical for assessing ecological risks, potential pollutant transport, and the viability of recovery or mitigation strategies for hazardous materials such as munitions. Accurate burial depth estimation from remote imagery remains difficult due to partial occlusion, poor visibility, and object degradation. This work introduces a computer vision pipeline, called PoseIDON, which combines deep foundation model features with multiview photogrammetry to estimate six degrees of freedom object pose and the orientation of the surrounding seafloor from ROV video. Burial depth is inferred by aligning CAD models of the objects with observed imagery and fitting a local planar approximation of the seafloor. The method is validated using footage of 54 objects, including barrels and munitions, recorded at a historic ocean dumpsite in the San Pedro Basin. The model achieves a mean burial depth error of approximately 10 centimeters and resolves spatial burial patterns that reflect underlying sediment transport processes. This approach enables scalable, non-invasive mapping of seafloor burial and supports environmental assessment at contaminated sites.