Abstract:

Low-light images often suffer from insufficient brightness， severe noise， detail loss， and color distortion， which significantly degrade visual quality and hinder the performance of subsequent vision tasks. To address these issues， a Low-Light Image Enhancement （LLIE） Network based on Lightweight Residual and Brightness-aware Dynamic feature fUsion （LRBDU-Net） was proposed. Firstly， a Lightweight Residual Feature Extraction （LRFE） module was designed in the encoding stage to mitigate information loss caused by downsampling and improve the extraction capability for low-light features. Secondly， a Brightness-aware Deep Semantic feature Processing （BDSP） module was designed in the encoding and decoding transition stage to strengthen the network’s perception and restoration abilities of brightness distribution of low-light images. Thirdly， a lightweight Dynamic Feature Fusion （DFF） mechanism was applied in the decoding stage to enhance the fusion effect of skip-connected and upsampled features， thereby improving network’s noise suppression and detail restoration abilities of low-light images. Fourthly， a Perception-Color Hybrid loss function （PCH） was proposed to further enhance structural consistency and color reproduction degree of LLIE. Finally， a combined structure of Group convolution and Ghost convolution （GpGh） was used to perform lightweight network design， thereby ensuring quality of LLIE and improving computational efficiency at the same time. Experimental results on the LOL （LOw-Light） datasets （LOL-v1， LOL-v2-real， and LOL-v2-syn） demonstrate that the proposed network achieves the Peak Signal-to-Noise Ratio （PSNR） of 23.71 dB， 21.46 dB， and 24.80 dB， respectively， and the Structural SIMilarity index （SSIM） of 0.852， 0.863， and 0.933， respectively. Overall， this network adopts pure convolutional architecture and lightweight design. Compared with the lightweight deep curve estimation method — Zero-reference Deep Curve Estimation （Zero-DCE） network， this network achieves significantly better quality of LLIE； compared with LLIE Generative Adversarial Network based on attention mechanism — EnGAN （Enlighten Generative Adversarial Network）， and LLIE method based on Transformer — LLFormer （Low-Light Transformer）， this network reduces model complexity and inference calculation cost significantly while maintaining high LLIE performance. It can be seen that the proposed network balances LLIE performance such as brightness improvement， noise suppression， detail restoration， structural integrity， and color reproduction degree with network computational efficiency well.

Key words: Low-Light Image Enhancement (LLIE), lightweight residual feature extraction, brightness awareness, dynamic feature fusion, lightweight network design, hybrid loss function

摘要：

针对低光图像常存在亮度不足、噪声大、细节丢失和颜色失真等问题，进而显著降低视觉质量，阻碍后续视觉任务的执行的事实，提出一种基于轻量残差与亮度感知动态特征融合的低光图像增强（LLIE）网络（LRBDU-Net）。首先，在编码阶段，设计一种基于轻量残差结构的特征提取（LRFE）模块，以缓解下采样过程造成的特征信息丢失，并提高对低光图像特征的提取能力；其次，在编解码过渡阶段，设计一种基于亮度感知的深层语义特征处理（BDSP）模块，以增强网络对低光图像亮度分布的感知和恢复能力；再次，在解码阶段，采用轻量级动态特征融合（DFF）机制，提升跳跃连接特征与上采样特征的融合效果，从而提高网络对低光图像的噪声抑制和细节恢复能力；继次，提出一种基于感知-颜色的混合损失函数（PCH），从而进一步提高LLIE的结构一致性与色彩还原度；最后，采用分组卷积与Ghost卷积的组合结构（GpGh）对网络进行轻量化设计，从而在保证LLIE质量的同时降低网络复杂度。实验结果表明，所提网络在LOL （LOw-Light）系列数据集（LOL-v1、LOL-v2-real和LOL-v2-syn）上的峰值信噪比（PSNR）分别达到了23.71 dB、21.46 dB和24.80 dB，结构相似性指数（SSIM）分别达到了0.852、0.863和0.933。整体上，该网络采用纯卷积算子架构与轻量化设计，与轻量级深度曲线估计方法——零参考深度曲线估计（Zero-DCE）网络相比，在LLIE质量方面实现了显著的提升；与基于注意力机制的LLIE生成对抗网络EnGAN（Enlighten Generative Adversarial Network）和基于Transformer架构的LLIE方法LLFormer（Low-Light Transformer）相比，在保证LLIE性能的同时大幅降低了网络复杂度和推理计算开销。可见，所提网络能够在亮度提升、噪声抑制、细节恢复、结构完整性和色彩还原程度等LLIE性能与网络计算效率之间实现良好平衡。

关键词: 低光图像增强, 轻量残差特征提取, 亮度感知, 动态特征融合, 轻量化网络设计, 混合损失函数