Wave-Mamba: Wavelet State Space Model for Ultra-High-Definition Low-Light Image Enhancement

Wenbin Zou, Hongxia Gao, Weipeng Yang, Tongtong Liu

Abstract: Ultra-high-definition (UHD) technology has attracted widespread attention due to its exceptional visual quality, but it also poses new challenges for low-light image enhancement (LLIE) techniques. UHD images inherently possess high computational complexity, leading existing UHD LLIE methods to employ high-magnification downsampling to reduce computational costs, which in turn results in information loss. The wavelet transform not only allows downsampling without loss of information, but also separates the image content from the noise. It enables state space models (SSMs) to avoid being affected by noise when modeling long sequences, thus making full use of the long-sequence modeling capability of SSMs. On this basis, we propose Wave-Mamba, a novel approach based on two pivotal insights derived from the wavelet domain: 1) most of the content information of an image exists in the low-frequency component, less in the high-frequency component. 2) The high-frequency component exerts a minimal influence on the outcomes of low-light enhancement. Specifically, to efficiently model global content information on UHD images, we proposed a low-frequency state space block (LFSSBlock) by improving SSMs to focus on restoring the information of low-frequency sub-bands. Moreover, we propose a high-frequency enhance block (HFEBlock) for high-frequency sub-band information, which uses the enhanced low-frequency information to correct the high-frequency information and effectively restore the correct high-frequency details. Through comprehensive evaluation, our method has demonstrated superior performance, significantly outshining current leading techniques while maintaining a more streamlined architecture. The code is available at https://github.com/AlexZou14/Wave-Mamba.

Primary Subject Area: [Content] Vision and Language

Secondary Subject Area: [Experience] Multimedia Applications, [Content] Multimodal Fusion

Relevance To Conference: Ultra-High Definition (UHD) image enhancement under low-light conditions is a rapidly evolving research area in the field of computer vision and digital image processing. This area of study is motivated by the increasing prevalence of UHD imaging technologies across a wide range of applications, from consumer electronics like smartphones and digital cameras to professional settings such as broadcasting, surveillance, and medical imaging. UHD images, with their high resolution and detail, offer significant advantages in clarity and visual quality. However, capturing high-quality UHD images in low-light environments remains a challenging task due to limitations in sensor technology and the physics of light. These challenges include increased noise, color distortion, loss of detail, and motion blur, all of which degrade the image quality significantly. Research into enhancing UHD images under low-light conditions holds substantial promise for a wide array of applications, driving technological advancements, improving consumer experiences, and opening new avenues for professional and creative endeavors. It addresses a critical need in digital imaging, pushing the boundaries of what is visually achievable in low-light environments.

Submission Number: 4863