Skip to main content
zenodoopen

BVI-Coral: Underwater scenes for 3D reconstruction

<p>The BVI-Coral dataset was captured underwater specifically for 3D reconstruction, with the videos being moved around the target.</p> <p>There are two sets available: the original videos (Originalxxxxx) and the edited versions (HDxxxxx).</p> <p>Please cite our work:</p> <ul> <li>H. Wang, N. Anantrasirichai, F. Zhang and D. Bull, "<a href="https://www.computer.org/csdl/proceedings-article/wacv/2025/108300d287/25Km5swfXQQ">UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction</a>," <em>IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)</em>, 2025.</li> <li>L. Gough, A. Azzarelli, F. Zhang, N. Anantrasirichai, "<a href="https://arxiv.org/html/2502.16351v1">AquaNeRF: Neural Radiance Fields in Underwater Media with Distractor Removal,</a>" <em>IEEE International Symposium on Circuits and Systems, </em>2025.</li> </ul>

ShareScore

32/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
4
Harmonization
4
Access
16
Reuse readiness
8
Engagement
0