Lightweight Low-Light Enhancement Network with Multi-Bio-Inspired Visual Mechanisms

In edge deployment scenarios, low-light image enhancement faces a trade-off between model complexity and perceptual quality, limiting lightweight models under resource constraints. To address this problem, this paper proposes a perceptual quality optimization model inspired by biological visual mechanisms. Specifically, a GT-Mean loss is introduced to simulate the luminance adaptation property of the mammalian retina, effectively mitigating optimization bias caused by exposure inconsistency in imaging sensors, while the LPIPS loss, aligned with the perceptual preferences of the human visual system (HVS), is incorporated to enhance subjective visual quality. From a structural perspective, inspired by the multi-scale perception of insect compound eyes, biologically selective attention, and color constancy mechanisms, the proposed model integrates an efficient texture-aware attention module, an enhanced multi-scale feature fusion strategy, and a chrominance denoising module. Experimental results demonstrate that, while maintaining an extremely low parameter count of only 0.52 M, the proposed model consistently outperforms existing lightweight methods on the LOL series datasets in terms of PSNR, SSIM, and LPIPS. This work provides an efficient perceptual quality optimization solution for bioinspired visual sensing under resource-constrained conditions.