ResGASP-GAN: A Residual Group-Normalized ASPP-SE GAN with a PatchGAN Discriminator for Low-Light Image Enhancement

Engineering notes

The results indicate that the proposed method achieves competitive structural similarity and visual image quality on LOL-v2-Real, competitive reconstruction performance on LOL-v1, and good generalization on LOL-v2-Synthetic, with the second-best metrics of PSNR = 22.30 dB, SSIM = 0.9154, and LPIPS = 0.1022 among the reported methods on this last dataset.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

Low-light color image enhancement remains a challenging task for vision-based decision systems, which must simultaneously address illumination correction, noise suppression, contrast recovery, and color preservation from a single degraded observation. This study proposes ResGASP-GAN, a GAN-based low-light image enhancement framework built around a residual-output generator that integrates batch-size-independent normalization, multi-scale contextual aggregation, and channel-wise feature recalibration within a conditional adversarial setting. Group Normalization is integrated into the proposed generator to reduce dependence on batch statistics during small-batch training, while a Squeeze-and-Excitation (SE) module adaptively enables channel-wise feature recalibration and helps preserve structural and chromatic information. The proposed generator uses reflection-padded convolutions to reduce boundary artifacts, and it features a multi-scale bottleneck composed of dilated residual blocks and Atrous Spatial Pyramid Pooling to capture spatially varying illumination patterns. The model is optimized using a compound objective that combines an adversarial term with an ℓ1 reconstruction loss, balancing perceptual realism with pixel-level fidelity. Experimental evaluation employed the LOL-v1, LOL-v2-Real, and LOL-v2-Synthetic datasets using reference-based metrics: PSNR, SSIM, and LPIPS. No-reference perceptual metrics were also used, including NIQE and BRISQUE. The results indicate that the proposed method achieves competitive structural similarity and visual image quality on LOL-v2-Real, competitive reconstruction performance on LOL-v1, and good generalization on LOL-v2-Synthetic, with the second-best metrics of PSNR = 22.30 dB, SSIM = 0.9154, and LPIPS = 0.1022 among the reported methods on this last dataset. In contrast, using no-reference metrics, this study achieved very good results, with the lowest BRISQUE of 10.4540 and a competitive NIQE of 4.4396, providing high-quality visual–perceptual reconstruction. Overall, the proposed architecture provides a competitive GAN-based alternative for low-light image enhancement, combining residual connections, multi-scale contextual modeling, and channel-wise feature refinement. This architecture provides the lowest inference time over all discussed models, which is highly required in real-time outdoor applications such as robot navigation and mapping.

Links and sources

• PDF from original source

Comments