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

arXiv: https://arxiv.org/abs/2604.19133 · HTML: https://mlsanity.com/paper/2604.19133/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 25 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 10 of 10)

- [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021)
- [NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images](https://mlsanity.com/paper/2111.13679/) (2021)
- [WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting](https://mlsanity.com/paper/2408.08206/) (2024)
- [SeaSplat: Representing Underwater Scenes with 3D Gaussian Splatting and a Physically Grounded Image Formation Model](https://mlsanity.com/paper/2409.17345/) (2024)
- [Investigation of the Challenges of Underwater-Visual-Monocular-SLAM](https://mlsanity.com/paper/2306.08738/) (2023)
- [Design, Implementation and Evaluation of an External Pose-Tracking System for Underwater Cameras](https://mlsanity.com/paper/2305.04226/) (2023)
- [3D Gaussian Splatting aided Localization for Large and Complex Indoor-Environments](https://mlsanity.com/paper/2502.13803/) (2025)
- [Relative Illumination Fields: Learning Medium and Light Independent Underwater Scenes](https://mlsanity.com/paper/2504.10024/) (2025)
- [Optical Ocean Recipes: Creating Realistic Datasets to Facilitate Underwater Vision Research](https://mlsanity.com/paper/2509.20171/) (2025)
- [Impact of Underwater Image Enhancement on Feature Matching](https://mlsanity.com/paper/2507.21715/) (2025)

## Abstract (arXiv)

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