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 this https URL.
Abstract (translated)
超高清（UHD）技术因出色的图像质量而引起了广泛关注，但它同时也给低光图像增强（LLIE）技术带来了新的挑战。UHD图像固有高计算复杂性，导致现有UHD LLIE方法采用高倍率下采样来降低计算成本，但这也导致了信息损失。小波变换不仅允许无信息损失的降采样，而且将图像内容与噪声分离。它使得状态空间模型（SSMs）在建模长序列时避免受到噪声的影响，从而充分利用SSMs的长期建模能力。在此基础上，我们提出了Wave-Mamba，一种基于小波域两个关键见解的新型方法：1）图像的大部分内容信息存在于低频分量中，而高频分量中的信息较少。2）高频分量对低光增强结果的影响最小。具体来说，为了有效地建模UHD图像的全球内容信息，我们通过提高SSMs关注低频子带的信息来提出了低频状态空间块（LFSSBlock）。此外，我们还提出了高频增强块（HFEBlock）来处理高频子带信息，它利用增强的低频信息来纠正高频信息，并有效恢复正确的高频细节。通过全面的评估，我们的方法已经证明了卓越的性能，显著超越了当前的主导技术，同时具有更简洁的架构。代码可在此链接处获取：https://www.acm.org/dl/d/161812012
URL
https://arxiv.org/abs/2408.01276
