MirrorDistill：用于高效低光复原的照度感知潜在蒸馏

中文摘要 AI 辅助

低光图像增强（LLIE）是视觉传感系统在退化光照条件下运行的重要组件，这些系统包括夜间监控、自主导航、遥感以及光照不良的工业环境中的检查。大多数LLIE方法依赖于输出级重建损失，该损失仅监督最终复原图像，导致中间特征恢复过程约束较弱。本文提出MirrorDistill，一种通过特征镜像连接低光和干净域的照度感知潜在蒸馏框架。在训练期间，共享编码器和指数移动平均教师解码器处理干净参考图像以生成干净域潜在目标。这些目标在两个层面监督低光学生网络：原始编码器特征和标准化多尺度解码器投影。对齐逐层应用，同时提出的照度感知加权方案对曝光不足区域给予更大重视。教师和参考分支仅在训练期间使用，因此推理仅需要轻量级学生编码器-解码器，不引入教师侧计算成本。在标准LOL基准上的评估中，MirrorDistill在真实拍摄的LOL-v2-Real数据集上优于最先进方法，同时具有最低的计算复杂度（GMACs），并在LOL-v1和LOL-v2-Synthetic数据集上保持竞争力。消融研究进一步展示了编码器镜像、解码器镜像和照度感知加权的贡献。最后，我们开源代码以惠及未来研究。

英文摘要

Low-light image enhancement (LLIE) is an im- portant component of visual sensing systems operating under degraded illumination, including nighttime surveillance, au- tonomous navigation, remote sensing, and inspection in poorly lit industrial environments. Most LLIE methods rely on output- level reconstruction losses that supervise only the final restored image, leaving the intermediate feature recovery process weakly constrained. This paper proposes MirrorDistill, an illumination- aware latent distillation framework that links the low-light and clean domains through feature mirroring. During training, a shared encoder and an exponential-moving-average teacher decoder process the clean reference image to generate clean- domain latent targets. These targets supervise the low-light student at two levels: raw encoder features and standardized multi-scale decoder projections. The alignment is applied layer by layer, while a proposed illumination-aware weighting scheme gives greater emphasis to underexposed regions. The teacher and reference branches are used only during training, so inference requires only the lightweight student encoder-decoder and in- troduces no teacher-side computational cost. Under evaluation on the standard LOL benchmarks, MirrorDistill outperforms the state-of-the-art methods on the real-captured LOL-v2-Real set, while having the lowest compute complexity (GMACs) and while remaining competitive on the LOL-v1 and LOL-v2-Synthetic datasets. Ablation studies further show the contributions of the encoder mirror, decoder mirror, and illumination-aware weighting. Finally, we release our code as open-source for the benefit of future research.

发表机构

• Hamad Bin Khalifa University（哈马德·本·哈利法大学）
• Universiti Malaysia Perlis（马来西亚玻璃市大学）
• Vrije Universiteit Brussel（布鲁塞尔自由大学）

机构由 AI 辅助整理，请以论文原文为准。