用于超高清水下图像增强的动态频谱Transformer（Dynamic SpectraFormer）
Dynamic SpectraFormer for Ultra-High-Definition Underwater Image Enhancement
- Research Institute for Science & Technology, Tokyo University of Science（东京理科大学科学技术研究所）
- Tokyo Institute of Technology（东京工业大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
针对水下图像的高低频混合失真问题，提出Dynamic SpectraFormer模型，通过超分辨率稀疏频谱注意力模块和动态频谱权重生成层实现增强，经多基准验证其有效性。
中文摘要 AI 辅助
水下图像因水中光的折射和吸收而存在色彩失真、 haze（ haze 译为 haze 保留）以及能见度差的问题，这些挑战严重影响自主水下航行器（AUV）或海洋机器人的应用。通常，色彩和亮度失真出现在低频段，而边缘和纹理失真则普遍存在于高频段。传统方法主要聚焦于空间域，难以同时校正这些混合失真。为解决这些问题，我们提出了动态频谱Transformer（Dynamic SpectraFormer），该模型通过频域Transformer实现水下图像增强。Dynamic SpectraFormer引入了超分辨率稀疏频谱注意力模块，可在不丧失通用逼近能力的情况下捕获长期依赖关系；此外，我们还开发了动态频谱权重生成层，作为自适应频谱带选择器，突出关键频谱带并抑制相关性较低的频谱带。因此，该方法通过同时处理高频和低频失真显著提升了水下图像质量。我们开展了大量 ablation 研究（ablation 保留）和对比评估，证实了 Dynamic SpectraFormer 在多个水下图像增强基准上的有效性，源代码可在指定网址获取。
英文摘要
Underwater images suffer from color distortion, haze, and poor visibility due to light refraction and absorption in water. These challenges significantly impact the utilization of Autonomous Underwater Vehicles (AUVs) or marine robots. Typically, color and brightness distortions manifest at lower frequencies, while edge and texture distortions are prevalent at higher frequencies. Traditional methods struggle to concurrently rectify these mixed distortions as they primarily concentrate on the spatial domain. To address these issues, we introduce the Dynamic SpectraFormer, which enhances underwater images through a frequency domain transformer. The Dynamic SpectraFormer introduces an ultra-high-resolution sparse spectrum attention module, which could capture the long-term dependency without losing the universal approximating power. Additionally, we have developed a dynamic spectrum weight generation layer that serves as an adaptive spectrum band selector, accentuating critical frequency bands and suppressing less relevant ones. Consequently, this method significantly improves underwater image quality by addressing both high- and low-frequency distortions. Our extensive ablation studies and comparative evaluations consolidate the Dynamic SpectraFormer's efficacy across multiple underwater image enhancement benchmarks. The source code is available at https://github.com/arifence2024/DynamicSpectraFormer.git.
