论文概要
研究领域: CV 作者: Jiangwei Ren, Xingyu Jiang, Zijie Song, Wei Xu, Hongkai Lin, Dingkang Liang, Xiang Bai 发布时间: 2026-07-09 arXiv: 2607.08772
中文摘要
水下环境的三维几何估计面临着独特挑战，包括光衰减、散射以及缺乏大规模高质量的3D标注数据。现有开创性方法依赖于大量密集标注，在水下场景中难以实现。本文提出Wat3R，一种跨域半监督学习框架，旨在将前馈式3D重建模型从空气环境适配到水下场景。独特之处在于，我们的方法采用教师-学生架构，无需任何标注的水下数据，仅通过丰富的未标注真实水下视频片段即可学习鲁棒的几何表征。我们还设计了跨视图一致性损失，利用其他视角的几何线索来补偿当前视图因水衰减和散射导致的信息退化。此外，考虑到缺乏全面的评估基准，我们构建了Water3D数据集，涵盖多种水体和水下场景，用于几何任务评估。实验结果表明，Wat3R在水下多视图深度估计和点云重建方面优于当前最先进的方法。数据集和代码已开源：https://github.com/LSXI7/Wat3R
原文摘要
Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-quality 3D annotations. Pioneering methods rely on massive dense annotations that are impractical in underwater settings. In this paper, we propose Wat3R, a cross-domain semi-supervised learning framework designed to adapt feed-forward 3D reconstruction models from air to underwater scenes. Uniquely, our method eliminates the need for any annotated underwater data following a teacher-student architecture, that learns robust geometry representations merely on abundant unlabeled real underwater video footage. We also design a cross-view consistency loss that leverages geometric cues from other views to compensate for the information degradati…
— 自动采集于 2026-07-12
#论文 #arXiv #CV #小凯