arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.00872cs.CV
收藏

无畏亮度自适应:用于曝光校正的宏微分层 Transformer

Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction

Dalian University of Technology(大连理工大学);Peng Cheng Laboratory(鹏城实验室)

Gehui Li, Jinyuan Liu, Long Ma, Zhiying Jiang, Xin Fan, Risheng Liu

AI总结:

针对复杂曝光误差及卷积在极端过曝、欠曝区域恢复能力不足的问题,提出融合宏微注意力与分层由粗到细校正的 Transformer,并用对比约束改善色彩和细节。

摘要:

在不理想的曝光设置下拍摄的照片通常呈现较差的视觉质量。由于校正过程差异显著,单个神经网络很难处理所有曝光问题。此外,卷积固有的局限性阻碍了模型在严重过曝或欠曝区域恢复真实色彩或细节的能力。为克服这些限制,我们提出了一种 Macro-Micro-Hierarchical transformer,它由用于捕获长程依赖的宏注意力、用于提取局部特征的微注意力,以及用于由粗到细校正的分层结构组成。具体而言,互补的宏—微注意力设计在允许全局交互的同时增强了局部性。分层结构使网络能够逐层校正不同尺度的曝光误差。此外,我们提出了一种对比约束,并将其无缝耦合到损失函数中,使校正后的图像被拉向正样本,并被推离动态生成的负样本,从而消除残余的色彩失真和细节丢失。我们还将该方法扩展为图像增强器,用于低光人脸识别和低光语义分割。实验表明,我们的方法在定量和定性上均取得了比现有最先进方法更具吸引力的结果。

英文摘要:

Photographs taken with less-than-ideal exposure settings often display poor visual quality. Since the correction procedures vary significantly, it is difficult for a single neural network to handle all exposure problems. Moreover, the inherent limitations of convolutions, hinder the models ability to restore faithful color or details on extremely over-/under- exposed regions. To overcome these limitations, we propose a Macro-Micro-Hierarchical transformer, which consists of a macro attention to capture long-range dependencies, a micro attention to extract local features, and a hierarchical structure for coarse-to-fine correction. In specific, the complementary macro-micro attention designs enhance locality while allowing global interactions. The hierarchical structure enables the network to correct exposure errors of different scales layer by layer. Furthermore, we propose a contrast constraint and couple it seamlessly in the loss function, where the corrected image is pulled towards the positive sample and pushed away from the dynamically generated negative samples. Thus the remaining color distortion and loss of detail can be removed. We also extend our method as an image enhancer for low-light face recognition and low-light semantic segmentation. Experiments demonstrate that our approach obtains more attractive results than state-of-the-art methods quantitatively and qualitatively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑