Abstract
Recent advancements in Low-Light Image Enhancement (LLIE) have focused heavily on Diffusion Probabilistic Models, which achieve high perceptual quality but suffer from significant computational latency (often exceeding 2-4 seconds per image). Conversely, traditional CNN-based baselines offer real-time inference but struggle with "over-smoothing," failing to recover fine structural details in extreme low-light conditions. This creates a practical gap in the literature: the lack of a model that provides generative-level texture recovery at edge-deployable speeds. In this paper, we address this trade-off by proposing a hybrid Attention U-Net GAN. We demonstrate that the heavy iterative sampling of diffusion models is not strictly necessary for texture recovery. Instead, by integrating Attention Gates into a lightweight U-Net backbone and training within a conditional adversarial framework, we can approximate the high-frequency fidelity of generative models in a single forward pass. Extensive experiments on the SID dataset show that our method achieves a best-in-class LPIPS score of 0.112 among efficient models, significantly outperforming efficient baselines (SID, EnlightenGAN) while maintaining an inference latency of 0.06s. This represents a 40x speedup over latent diffusion models, making our approach suitable for near real-time applications.
Abstract (translated)
最近在低光图像增强（LLIE）领域的进展主要集中在扩散概率模型上，这类模型虽然能够达到很高的感知质量，但计算延迟严重（每张图片处理时间往往超过2-4秒）。相比之下，传统的基于CNN的方法则能提供实时推理，但在极端低光照条件下却难以避免“过度平滑”问题，无法恢复精细的结构细节。这在文献中造成了一个实际差距：缺乏既能生成高质量纹理又能实现边缘部署速度的模型。 在这篇论文中，我们通过提出一种混合注意力U-Net GAN来解决上述权衡问题。我们证明了扩散模型中的密集迭代采样并非进行纹理恢复所必需。相反，通过将注意力门控集成到轻量级U-Net骨干网络，并在条件对抗框架内训练，可以在一次前向传递中近似生成模型的高频保真度。 我们在SID数据集上的广泛实验表明，我们的方法达到了0.112的最佳LPIPS分数（在高效模型类别中），远超其他高效基准（如SID和EnlightenGAN）的表现，并且保持了0.06秒的推理延迟。这代表了对潜在扩散模型40倍的速度提升，使得我们的方法适用于近乎实时的应用场景。
URL
https://arxiv.org/abs/2601.06518
