Image-Space Refraction Correction for Underwater 3D Reconstruction: Warping Flat-Port Views into Pinhole Perspective

Key points

• Consumer-grade cameras in flat-port housings are widely used for underwater exploration and mapping of coral reefs and seafloor habitats due to their low cost and accessibility.1
• However, refraction at flat-port interfaces causes bowl-shaped deformation in reconstructed scenes and camera trajectories, compromising the metric accuracy required for mapping and navigation.1
• Our method is downstream-agnostic: the refraction-corrected images can be directly used as input to existing reconstruction and SLAM algorithms.1
• We characterize the refractive distortion through ray-tracing simulations and validate our correction on two real underwater datasets with differing scene structures.1

Sources (1)

• [1]Image-Space Refraction Correction for Underwater 3D Reconstruction: Warping Flat-Port Views into Pinhole Perspective
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 05:33 AM

  To remove the dominant refractive distortion before reconstruction, we introduce a physics-based refraction correction in image space.

  Consumer-grade cameras in flat-port housings are widely used for underwater exploration and mapping of coral reefs and seafloor habitats due to their low cost and accessibility.

Extractive summary: sentences quoted from the sources.