Dynamic SpectraFormer for Ultra-High-Definition Underwater Image Enhancement

Zhiqiang Hu; Tao Yu; Shouren Huang; Masatoshi Ishikawa

cs.CVAug 19, 2026

Dynamic SpectraFormer for Ultra-High-Definition Underwater Image Enhancement

Authors: Zhiqiang Hu, Tao Yu, Shouren Huang, Masatoshi Ishikawa

Organizations: Research Institute for Science & Technology, Tokyo University of Science · Tokyo Institute of Technology

Abstract

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.

Figures & tables

Fig. 1: The difference of the DCT spectrum between a pair of underwater image and its enhanced image in LSUI [ 29 ] dataset. Where (a) are the image pairs, (b) the corresponding DCT spectrum and the difference. The enhanced image contains more high frequencies compared with the original image.

Fig. 2: Dynamic SpectraFormer is configured with a multi-scale U-shape architecture for restoring high-definition underwater images.

Fig. 3: Dynamic SpectraFormer Block with sparse spectrum attention. We first convert the query ( $\mathbf{Q}$ ), key ( $\mathbf{K}$ ), and value ( $\mathbf{V}$ ) matrices into the frequency domain by using the Discrete Cosine Transform (DCT). Next, a Dynamic Spectrum Weight Generator (DSWG) adaptively selects $K$ frequency bands based on the input underwater image’s features. Thirdly, we use the sparsified $\mathbf{Q}$ and $\mathbf{K}$ matrices to compute the attention. Finally, we use the inverse DCT (iDCT) to transform the value matrix ( $\mathbf{V}$ ) to the spatial domain. Using sparse attention in the DCT domain, the Dynamic SpectraFormer with global attention capability could capture long-term dependency without sacrificing its universal approximation power.

Fig. 4: The Dynamic Spectrum Weights Generator. Our DSWG module aims to produce dynamic spectrum weights $\bm{M}$ to modify the frequency bands of the transformed DCT, and plays a role as a frequency band enhancer.

Method	PSNR			SSIM			Params	FLOPs
	(UIEB — LSUI — EUVP)			(UIEB — LSUI — EUVP)			(M)	(GFLOPs)
Ucolor [ 21 ]	$20.78$	$22.91$	-	$0.8713$	$0.8902$	-	157M	$443.85$ G
WaterNet [ 22 ]	$19.81$	$17.73$	20.14	$0.8612$	$0.8223$	0.68	25M	$193.7$ G
UGAN [ 6 ]	$20.68$	$19.79$	23.49	$0.8430$	$0.7843$	0.7802	57M	$38.97$ G
FUnIE-GAN [ 16 ]	$19.45$	$19.37$	23.40	$0.8602$	$0.8401$	0.8420	7M	$10.23$ G
Deep SESR [ 15 ]	-	-	24.21	-	-	0.8401	3M	$29.32$ G

TABLE I: Quantitative comparison on the UIEB, LSUI, and EUVP underwater datasets. Note that the FLOPs is calculated with image size

256\times 256

pixels. The best results are shown in bold text.

Fig. 5: Visual comparison on the underwater dataset.

Fig. 6: The images from LSUI data set [ 29 ] with corresponding dynamic spectrum weights. For the images containing rich details, as shown in (b), the generated dynamic spectrum weight mostly focuses on the high-frequency bands, while for the plain images (a), dynamic spectrum weight emphasizes the low-frequency bands on the contrary. To this end, our Dynamic Spectrum Weights Generator could adaptively reweight the high-frequency and low-frequency components concerning the image content and facilitate the token mixing operation. Note that the lighter the color, the larger the spectrum weight.

Modules	UIEB		LSUI		EUVP
	PSNR	SSIM	PSNR	SSIM	PSNR	SSIM
Random spectrum band	21.01	0.8402	24.19	0.8105	27.20	0.8321
All-pass filter	23.72	0.8461	25.20	0.8753	28.09	0.8654
Dynamic Spectrum Weight Generator	25.98	0.9341	26.33	0.9327	29.78	0.8848

TABLE II: Effectiveness of the Dynamic Spectrum Weights Generator in Dynamic SpectraFormer on three datasets.

Spectrum length (top- K )	UIEB		LSUI		EUVP
	PSNR	SSIM	PSNR	SSIM	PSNR	SSIM
8	19.45	0.8657	19.71	0.7812	19.32	0.7782
16	22.19	0.9038	23.74	0.8462	26.22	0.8578
32	24.23	0.9212	24.82	0.8570	28.01	0.8721
64	25.98	0.9341	26.33	0.9327	29.78	0.8848
128	26.00	0.9340	26.33	0.9329	29.82	0.8810

TABLE III: Effectiveness of the Sparsity of Sparse Spectrum Attention.

Fig. 7: Comparisons among ViT [ 4 ] , U-Shape Transformer [ 29 ] and our Dynamic SpectraFormer in (a) FLOPs (b) memory consumption concerning different image resolutions. The time and memory complexity of the ViT increase quadratically with the spatial resolution of input $\mathcal{O}(W^{2}H^{2})$ , while our method significantly lowers the computational complexity, as shown in the figure.

Explore similar work

Hero-Mamba: Mamba-based Dual Domain Learning for Underwater Image Enhancement
Apr 17, 2026Tejeswar Pokuri, Shivarth RaiUnderwater Image Enhancement Underwater Imaging
Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal - 576104, India
Physics-Guided Spectral Distillation for Underwater Image Enhancement on Resource-Constrained Devices
Sep 28, 2026Yifan Chen, Kai He, Ye Zheng +3Image Enhancement Underwater Image Enhancement
College of Future Information Technology, Fudan University, Shanghai 200433, China · Institute of Artificial Intelligence (TeleAI), China Telecom, China · School of Computer Science and Technology, Harbin Institute of Technology, Weihai 264209, China
Advancing Visual Reliability: Color-Accurate Underwater Image Enhancement for Real-Time Underwater Missions
Mar 17, 2026Yiqiang Zhou, Yifan Chen, Zhe Sun +3Image Enhancement Underwater Image Enhancement
Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China · College of Computer and Control Engineering, Northeast Forestry University, Harbin, 150040, China · College of Future Information Technology, Fudan University, Shanghai 200433, China +2

Apr 17, 2026J/K move · Enter open · S save

Hero-Mamba: Mamba-based Dual Domain Learning for Underwater Image Enhancement

Tejeswar Pokuri, Shivarth Rai

Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal - 576104, India

Underwater Image Enhancement Underwater Imaging

Open paper AskPDF arXiv

Underwater images often suffer from severe degradation, such as color distortion, low contrast, and blurred details, due to light absorption and scattering in water. While learning-based methods like CNNs and Transformers have shown promise, they face critical limitations: CNNs struggle to model the long-range dependencies needed for non-uniform degradation, and Transformers incur quadratic computational complexity, making them inefficient for high-resolution images. To address these challenges, we propose Hero-Mamba, a novel Mamba-based network that achieves efficient dual-domain learning for underwater image enhancement. Our approach uniquely processes information from both the spatial domain (RGB image) and the spectral domain (FFT components) in parallel. This dual-domain input allows the network to decouple degradation factors, separating color/brightness information from texture/noise. The core of our network utilizes Mamba-based SS2D blocks to capture global receptive fields and long-range dependencies with linear complexity, overcoming the limitations of both CNNs and Transformers. Furthermore, we introduce a ColorFusion block, guided by a background light prior, to restore color information with high fidelity. Extensive experiments on the LSUI and UIEB benchmark datasets demonstrate that Hero-Mamba outperforms state-of-the-art methods. Notably, our model achieves a PSNR of 25.802 and an SSIM of 0.913 on LSUI, validating its superior performance and generalization capabilities.

Abstract

Explore similar work

Hero-Mamba: Mamba-based Dual Domain Learning for Underwater Image Enhancement

Physics-Guided Spectral Distillation for Underwater Image Enhancement on Resource-Constrained Devices

Advancing Visual Reliability: Color-Accurate Underwater Image Enhancement for Real-Time Underwater Missions