Cutting-edge 3D reconstruction solutions for underwater coral reef images: A review and comparison

TL;DR

This paper tackles the challenge of accurate 3D reconstruction of underwater coral reefs from images by systematically reviewing camera pose estimation and dense surface reconstruction methods, including traditional photogrammetry, deep learning, NeRF, and Gaussian Splatting. It benchmarks these techniques on real and synthetic coral datasets, revealing that learning-based feature extraction and matching, together with advanced MVS, generally outperform traditional approaches in underwater scenes, while NeRF- and GS-based methods excel under certain data-rich conditions but struggle with limited data. The study provides practical recommendations and discusses the potential for hybrid workflows to balance reconstruction quality and computational cost, particularly for large-scale reef surveys. It also highlights practical implications for reef monitoring, conservation, and management, emphasizing the need for robust evaluation metrics, richer datasets, and simulation-to-real transfer research. Overall, the work offers a technical foundation and actionable guidance for practitioners processing underwater reef imagery to produce high-fidelity 3D models.

Abstract

Corals serve as the foundational habitat-building organisms within reef ecosystems, constructing extensive structures that extend over vast distances. However, their inherent fragility and vulnerability to various threats render them susceptible to significant damage and destruction. The application of advanced 3D reconstruction technologies for high-quality modeling is crucial for preserving them. These technologies help scientists to accurately document and monitor the state of coral reefs, including their structure, species distribution and changes over time. Photogrammetry-based approaches stand out among existing solutions, especially with recent advancements in underwater videography, photogrammetric computer vision, and machine learning. Despite continuous progress in image-based 3D reconstruction techniques, there remains a lack of systematic reviews and comprehensive evaluations of cutting-edge solutions specifically applied to underwater coral reef images. The emerging advanced methods may have difficulty coping with underwater imaging environments, complex coral structures, and computational resource constraints. They need to be reviewed and evaluated to bridge the gap between many cutting-edge technical studies and practical applications. This paper focuses on the two critical stages of these approaches: camera pose estimation and dense surface reconstruction. We systematically review and summarize classical and emerging methods, conducting comprehensive evaluations through real-world and simulated datasets. Based on our findings, we offer reference recommendations and discuss the development potential and challenges of existing approaches in depth. This work equips scientists and managers with a technical foundation and practical guidance for processing underwater coral reef images for 3D reconstruction....

Figures (19)

• Figure 1: The pipeline for 3D surface reconstruction of coral reefs based on images.
• Figure 2: A flexible framework for incremental Structure-from-Motion.
• Figure 3: A variety of dense surface reconstruction technologies applicable to coral reefs.
• Figure 4: The overview of experimental datasets.
• Figure 5: Visualization of the matching results of coral reef images with rotation and translation. The correct matches are depicted with green lines, while mismatches are represented with red lines. To ensure clarity, up to 400 matches are randomly selected from each result for display.