用轻量注意力U-NetGAN实现低光图像实时增强，兼顾细节恢复与速度。
Bridging Robustness and Efficiency: Real-Time Low-Light Enhancement via Attention U-Net GAN
- 融合注意力门的轻量U-Net在单次前向传播中完成增强
- 在SID数据集上达到0.112的LPIPS，比高效模型更优
- 0.06秒推理延迟，比扩散模型快40倍，适合边缘部署
低光图像增强（LLIE）近年多聚焦于扩散概率模型，虽能提供高感知质量但计算延迟大（常超2-4秒/图）。传统CNN基线虽可实时推理，却存在过度平滑问题，难以恢复极端暗光下的精细结构。本文提出一种混合注意力U-Net GAN，证明扩散模型的迭代采样并非纹理恢复所必需。通过将注意力门嵌入轻量U-Net骨干网络，并在条件对抗框架下训练，可在单次前向传播中逼近生成模型的高频保真度。在SID数据集上的实验表明，该方法在高效模型中取得最佳的LPIPS得分0.112，显著优于高效基线（SID、EnlightenGAN），同时保持0.06秒推理延迟，相较潜在扩散模型提速40倍，适用于近实时应用场景。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。