构建高分辨率水下图像修复数据集，提升浅海测深成图精度
Sea-Undistort: A Dataset for Through-Water Image Restoration in High Resolution Airborne Bathymetric Mapping
- 用Blender合成1200对512x512水下图像，含真实波浪、反光与散射效果
- 基于该数据集训练的轻量扩散模型，在真实航拍数据中显著降低测深误差
- 适合从事水下视觉、遥感测深或图像修复的研究者使用
浅水区基于图像的精确测深仍面临挑战，主要源于动态水面、水体特性与太阳光照带来的复杂光学畸变。本文提出Sea-Undistort，一个包含1200对512×512像素的合成水下场景数据集，由Blender生成，每对包含无畸变与有畸变视图，涵盖真实水面反光、波浪和散射等效果，并覆盖多样海底类型。每幅图像附带相机参数、太阳位置和平均水深等元数据，支持监督训练。利用该数据集，我们评估了两种先进图像修复方法，并提出一种融合早期反光掩码的轻量级扩散模型。在真实航空数据上，该模型生成更完整的海底数字表面模型（DSMs），尤其在深水区域表现更好，有效降低测深误差，抑制反光与散射，清晰恢复海底细节。数据集、模型权重与代码已公开于https://www.magicbathy.eu/Sea-Undistort.html。
原文摘要 · Abstract (English)
Accurate image-based bathymetric mapping in shallow waters remains challenging due to the complex optical distortions such as wave induced patterns, scattering and sunglint, introduced by the dynamic water surface, the water column properties, and solar illumination. In this work, we introduce Sea-Undistort, a comprehensive synthetic dataset of 1200 paired 512x512 through-water scenes rendered in Blender. Each pair comprises a distortion-free and a distorted view, featuring realistic water effects such as sun glint, waves, and scattering over diverse seabeds. Accompanied by per-image metadata such as camera parameters, sun position, and average depth, Sea-Undistort enables supervised training that is otherwise infeasible in real environments. We use Sea-Undistort to benchmark two state-of-the-art image restoration methods alongside an enhanced lightweight diffusion-based framework with an early-fusion sun-glint mask. When applied to real aerial data, the enhanced diffusion model delivers more complete Digital Surface Models (DSMs) of the seabed, especially in deeper areas, reduces bathymetric errors, suppresses glint and scattering, and crisply restores fine seabed details. Dataset, weights, and code are publicly available at https://www.magicbathy.eu/Sea-Undistort.html.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。