Night time semantic segmentation is a crucial task in computer vision, focusing on accurately classifying and segmenting objects in low-light conditions. Unlike daytime techniques, which often perform worse in nighttime scenes, it is essential for autonomous driving due to insufficient lighting, low illumination, dynamic lighting, shadow effects, and reduced contrast. We propose RHRSegNet, implementing a relighting model over a High-Resolution Network for semantic segmentation. RHRSegNet implements residual convolutional feature learning to handle complex lighting conditions. Our model then feeds the lightened scene feature maps into a high-resolution network for scene segmentation. The network consists of a convolutional producing feature maps with varying resolutions, achieving different levels of resolution through down-sampling and up-sampling. Large nighttime datasets are used for training and evaluation, such as NightCity, City-Scape, and Dark-Zurich datasets. Our proposed model increases the HRnet segmentation performance by 5% in low-light or nighttime images.

翻译：夜间语义分割是计算机视觉中的一项关键任务，其核心在于低光照条件下对物体进行精确分类与分割。由于光照不足、照度低、动态光照、阴影效应以及对比度降低等问题，与通常在夜间场景表现不佳的日间技术不同，该任务对于自动驾驶至关重要。我们提出了RHRSegNet，在用于语义分割的高分辨率网络上实现了一个再光照模型。RHRSegNet采用残差卷积特征学习来处理复杂的照明条件。随后，我们的模型将光照增强后的场景特征图输入到一个用于场景分割的高分辨率网络中。该网络通过卷积生成具有不同分辨率的特征图，并借助下采样和上采样实现多级分辨率。训练与评估使用了大规模夜间数据集，例如NightCity、City-Scape和Dark-Zurich数据集。我们提出的模型在低光照或夜间图像上将HRnet的分割性能提升了5%。