Mapping Pamir: Multi-Session Visual-Inertial SLAM and 3D Reconstruction of an Underwater Shipwreck
2026-07-12 • Robotics
Robotics
AI summaryⓘ
The authors developed a way to create detailed 3D maps of underwater places using a cheap action camera combined with other sensors like a dive computer. They first build rough maps and camera paths for each dive session using SVIn2, then improve those maps globally with COLMAP to get a dense reconstruction. When special markers are present, these help align maps from different dive sessions into one coordinate system. They tested this method by mapping a shipwreck near Barbados, capturing both outside and inside areas across multiple dives, including a session using two different cameras.
Visual-Inertial SLAMStructure-from-MotionCOLMAPSVIn2Underwater MappingCoordinate TransformationAction Camera3D ReconstructionDive ComputerCalibration Targets
Authors
Michalis Chatzispyrou, Luke Horgan, Hyunkil Hwang, Harish Sathishchandra, Chinmay Burgul, Monika Roznere, Alberto Quattrini Li, Philippos Mordohai, Ioannis Rekleitis
Abstract
This paper presents a framework for multi-session mapping of underwater environments utilizing an affordable action camera. The Visual-Inertial data are augmented by water depth recordings from a dive computer. SVIn2, an open-source VI-SLAM framework, is utilized to generate a trajectory and a sparse reconstruction for each session. Utilizing the keyframes extracted from SVIn2 and the estimated camera poses, a Structure-from-Motion (SfM) framework, COLMAP, is employed for global optimization and to produce a dense reconstruction of the target environment. The presence of calibration targets at fixed locations, when available, is used to estimate the coordinate transformation between different data collection sessions, thus transforming the different sessions into the same coordinate frame. The proposed pipeline is employed for the mapping of a shipwreck off the coast of Barbados. For the first time, both the exterior and the accessible interior parts of the wreck were mapped in two sessions, while a third session employed two cameras with different fields of view.