Scene understanding is essential to robotic navigation and autonomous driving as it provides semantic information to their controlling system. However, it will fail when processing low‐light images/videos captured under adverse weather or at night use state‐of‐the‐art scene understanding methods. A naive way to directly infer semantics from low‐light images is ill posed because the low‐light condition distorts pixel intensities and buries details. In order to address this problem, we propose the Deep Intensity Manipulation Network (DIMNet), which could relight the input images and recover the details, and combine the DIMNet with a scene understanding network to get a cascaded network to learn the semantics from low‐light images. Through learning pixel intensity manipulation, our method can generate images not only visually pleasing but also practical for scene understanding. Qualitative and quantitative experiments demonstrate that the proposed method is effective and robust for both synthetic and real‐world images.

中文翻译：

---

具有深度强度操作的级联网络，用于场景理解

场景理解对于机器人导航和自动驾驶至关重要，因为它为其控制系统提供语义信息。但是，在处理在恶劣天气下或夜间使用最先进的场景理解方法捕获的低光图像/视频时，它会失败。一种从低光图像中直接推断语义的幼稚方法是不合适的，因为低光条件会扭曲像素强度并掩盖细节。为了解决这个问题，我们提出了深度强度操纵网络（DIMNet），它可以重新点亮输入图像并恢复细节，并将 DIMNet 与场景理解网络相结合，得到一个级联网络，从低层次学习语义。光图像。通过学习像素强度操作，我们的方法可以生成不仅视觉上令人愉悦的图像，而且对于场景理解也很实用。定性和定量实验表明，所提出的方法对于合成和现实世界的图像都是有效且稳健的。