Search papers, labs, and topics across Lattice.
The paper introduces BALTIC, a new benchmark for evaluating 3D reconstruction methods across air and underwater domains under varying illumination conditions. It systematically assesses Structure-from-Motion (SfM), Neural Radiance Fields (NeRF), and 3D Gaussian Splatting (3D-GS) using a controlled experimental setup with ground-truth pose estimation. Results indicate that 3D-GS, with basic preprocessing, can achieve comparable performance to specialized underwater methods in controlled settings, but its robustness diminishes in complex real-world scenarios.
Gaussian Splatting can surprisingly rival specialized underwater 3D reconstruction techniques with just basic color correction, but don't expect miracles in the murky depths of real-world environments.
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
