LCS-Net: Learnable Color Correction and Selective Multi-Scale Fusion for Underwater Image Enhancement

Underwater images are frequently degraded by wavelength-dependent absorption and scattering, which introduce strong color casts, reduce contrast, and obscure fine structures. Although learning-based enhancement methods have recently improved perceptual quality, many remain computationally intensive, limiting deployment on resource-constrained underwater platforms. To address this challenge, we propose LCS-Net, a lightweight framework for single underwater image enhancement that targets a favorable quality-efficiency trade-off. LCS-Net first applies a dynamic Learnable Color Correction Module (LCCM) that predicts image-specific correction parameters from global color statistics, enabling low-overhead cast compensation and stabilizing the input distribution. Feature extraction is conducted using efficient inverted residual blocks equipped with squeeze-and-excitation (SE) to recalibrate channel responses and facilitate detail recovery under scattering-induced degradation. At the bottleneck, a Selective Multi-Scale Dilated Block (SMSDB) aggregates complementary context via parallel dilated convolutions and global cues and adaptively reweights the fused features to handle diverse water conditions. Extensive experiments on public benchmarks demonstrate that LCS-Net achieves competitive performance, yielding a PSNR of 26.46 dB and an SSIM of 0.92 on UIEB, along with 28.71 dB and 0.86 on EUVP, while maintaining a compact model size and low computational cost, highlighting its potential for practical deployment.