Instance segmentation for low-light imagery remains largely unexplored due to
the challenges imposed by such conditions, for example shot noise due to low
photon count, color distortions and reduced contrast. In this paper, we propose
an end-to-end solution to address this challenging task. Based on Mask R-CNN,
our proposed method implements weighted non-local (NL) blocks in the feature
extractor. This integration enables an inherent denoising process at the
feature level. As a result, our method eliminates the need for aligned ground
truth images during training, thus supporting training on real-world low-light
datasets. We introduce additional learnable weights at each layer in order to
enhance the network's adaptability to real-world noise characteristics, which
affect different feature scales in different ways.
Experimental results show that the proposed method outperforms the pretrained
Mask R-CNN with an Average Precision (AP) improvement of +10.0, with the
introduction of weighted NL Blocks further enhancing AP by +1.0.

在这篇论文中，我们提出了一种端到端的解决方案来解决低光条件下的实例分割问题，通过在特征提取器中实现加权非局部（NL）块，我们的方法在特征级别上实现了内嵌的去噪过程，从而消除了训练时对齐的基准图像的需要，以支持在真实世界的低光数据集上进行训练，并引入了可学习的权重以增强网络对真实世界噪声特性的适应性，这些特性以不同的方式影响不同的特征尺度，实验结果表明，所提出的方法在平均精度（AP）上的改进为 + 10.0，加权 NL 块的引入进一步提高了 AP 的值，使得所提出的方法胜过预训练的 Mask R-CNN。