SPLASH-SegFormer Pipeline: A Transformer-Based Approach for High-Resolution and Low-Cost Laser Scanner Seafloor Mapping

Abstract

High-resolution seafloor mapping continues to be challenging, primarily due to the high costs and complexity of traditional sensors. Laser scanners offer a more affordable alternative, using a monocular camera and a laser stripe. While this method provides high-resolution 3D reconstructions, it is sensitive to underwater lighting and surface reflections. This work introduces SPLASH-SegFormer Pipeline, a novel method that leverages attention mechanisms and multi-level feature integration to enhance laser stripe segmentation in underwater environments, marking, to the best of our knowledge, the first application of a transformer-based architecture for this task. The proposed method is trained and evaluated using both simulated and field experimental data collected in a test tank and during multiple sea expeditions, allowing it to learn from diverse and challenging environments. A complete pipeline is constructed around this network, enabling the processing of images from a camera to a 3D point cloud reconstruction quickly and accurately. The results demonstrate that SPLASH-SegFormer significantly enhances segmentation robustness and accuracy while maintaining a reasonable speed. It outperforms traditional underwater thresholding by over 64 points in mIoU and surpasses all evaluated methods, achieving 6.6 points higher mIoU than Stripe Segmentor while running over 65% faster. This speed enhances efficiency and makes it ideal for real-time onboard applications, enabling millimeter-level underwater 3D reconstruction and high-resolution seafloor mapping using smaller, cost-effective sensors.