Abstract
Underwater photography presents significant inherent challenges including reduced contrast, spatial blur, and wavelength-dependent color distortions. These effects can obscure the vibrancy of marine life and awareness photographers in particular are often challenged with heavy post-processing pipelines to correct for these distortions. We develop an image-to-image pipeline that learns to reverse underwater degradations by introducing a synthetic corruption pipeline and learning to reverse its effects with diffusion-based generation. Training and evaluation are performed on a small high-quality dataset of awareness photography images by Keith Ellenbogen. The proposed methodology achieves high perceptual consistency and strong generalization in synthesizing 512x768 images using a model of ~11M parameters after training from scratch on ~2.5k images.
Abstract (translated)
水下摄影面临诸多固有挑战，包括对比度降低、空间模糊以及依赖波长的颜色失真。这些效果会遮蔽海洋生物的鲜艳色彩，并且摄影师常常需要面对繁重的后期处理流程来纠正这些问题。我们开发了一种图像到图像的流水线，通过引入合成腐蚀流水线并学习用基于扩散的方法逆转其影响，从而学会消除水下退化现象。训练和评估是在Keith Ellenbogen的一组高质量意识摄影的小型数据集上进行的。所提出的方法在使用约1100万个参数模型从头开始训练大约2500张图像后，在合成分辨率为512x768像素的图像时，达到了高度感知一致性和强大的泛化能力。
URL
https://arxiv.org/abs/2602.05163
