BALTIC: A Benchmark and Cross-Domain Strategy for 3D Reconstruction Across Air and Underwater Domains Under Varying Illumination

2026-04-21

AI Summary

This work addresses the limited robustness of cross-media 3D reconstruction—spanning air and underwater environments—under varying illumination and motion conditions. To this end, the authors introduce a benchmark platform comprising 13 datasets that encompass both media, three lighting conditions, and multiple acquisition modalities, enabling the first systematic evaluation of cross-media reconstruction performance. They propose a strategy that leverages a small number of aerial views to assist underwater reconstruction, integrating COLMAP for structure-from-motion, enhanced by Neural Radiance Fields and 3D Gaussian Splatting. High-precision ground-truth poses are provided via an HTC Vive tracker. Experiments demonstrate that, in controlled scenes with consistent textures and simple white-balance preprocessing, general-purpose methods can achieve reconstruction quality comparable to specialized underwater algorithms; however, robustness remains limited in complex real-world environments.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Robust 3D reconstruction across varying environmental conditions remains a critical challenge for robotic perception, particularly when transitioning between air and water. To address this, we introduce BALTIC, a controlled benchmark designed to systematically evaluate modern 3D reconstruction methods under variations in medium and lighting. The benchmark comprises 13 datasets spanning two media (air and water) and three lighting conditions (ambient, artificial, and mixed), with additional variations in motion type, scanning pattern, and initialization trajectory, resulting in a diverse set of sequences. Our experimental setup features a custom water tank equipped with a monocular camera and an HTC Vive tracker, enabling accurate ground-truth pose estimation. We further investigate cross-domain reconstruction by augmenting underwater image sequences with a small number of in-air views captured under similar lighting conditions. We evaluate Structure-from-Motion reconstruction using COLMAP in terms of both trajectory accuracy and scene geometry, and use these reconstructions as input to Neural Radiance Fields and 3D Gaussian Splatting methods. The resulting models are assessed against ground-truth trajectories and in-air references, while rendered outputs are compared using perceptual and photometric metrics. Additionally, we perform a color restoration analysis to evaluate radiometric consistency across domains. Our results show that under controlled, texture-consistent conditions, Gaussian Splatting with simple preprocessing (e.g., white balance correction) can achieve performance comparable to specialized underwater methods, although its robustness decreases in more complex and heterogeneous real-world environments

Problem

• 3D reconstruction
• cross-domain
• underwater
• illumination variation
• robotic perception

Innovation

• cross-domain 3D reconstruction
• underwater vision
• 3D Gaussian Splatting
• benchmark dataset
• radiometric consistency