SDUIE：基于定量-文本双重控制的半监督扩散水下图像增强
SDUIE: Semi-Supervised Diffusion for Underwater Image Enhancement with Quant-Text Dual Control
提出一种基于低秩适配权重合并的连续数值控制扩散模型，以及通过语义提示对齐实现文本引导增强的方法，可复用于其他需要细粒度可控的图像复原任务。
原文依据 SDUIE-Quant allows continuous, numerical adjustment of enhancement levels via low-rank adaptation weight merging within a dual-branch diffusion model.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论水下图像常因波长相关的光衰减而呈现主导的蓝绿色调。尽管现有增强方法已取得有前景的性能，但它们通常忽略了视觉偏好的主观性。为弥补这一空白，我们提出SDUIE，一种层级感知的半监督扩散框架，用于水下图像增强，通过定量和文本输入实现双重控制。SDUIE-Quant允许通过双分支扩散模型中的低秩适配权重合并，对增强级别进行连续数值调整。该模型包含一个在合成水下-陆地图像对上训练的有监督分支，以及一个旨在保留真实水下场景自然色调的自监督分支。在此基础上，SDUIE-Text通过将语义提示与视觉增强效果对齐，利用学习到的融合权重，引入直观的语言引导控制。这种双模态设计既提供了精确控制，又实现了灵活的用户偏好增强。实验结果表明，SDUIE达到了最优结果，同时更好地保留了传统方法常忽略的美学质量。源代码见 https://github.com/Xiaofeng-life/SDUIE。
英文原文摘要 1278 字符
Underwater images often exhibit dominant blue-green hues due to wavelength-dependent light attenuation. While existing enhancement methods have achieved promising performance, they typically overlook the subjective nature of visual preferences. To address this gap, we propose SDUIE, a level-aware Semi-supervised Diffusion framework for Underwater Image Enhancement that enables dual control through both quantitative and textual inputs. SDUIE-Quant allows continuous, numerical adjustment of enhancement levels via low-rank adaptation weight merging within a dual-branch diffusion model. This model comprises a supervised branch trained on synthetic underwater-terrestrial pairs and a self-supervised branch designed to preserve the natural hues of real-world underwater scenes. Building on this, SDUIE-Text introduces intuitive, language-guided control by aligning semantic prompts with visual enhancement effects, leveraging the learned fusion weights. This dual-modality design offers both precise control and flexible, user-preferred enhancement. Experimental results demonstrate that SDUIE achieves state-of-the-art results while better preserving the aesthetic qualities often missed by conventional methods. The source code is in https://github.com/Xiaofeng-life/SDUIE.