Depth completion is the task of recovering dense depth maps from sparse ones, usually with the help of color images. Existing image-guided methods perform well on daytime depth perception self-driving benchmarks, but struggle in nighttime scenarios with poor visibility and complex illumination. To address these challenges, we propose a simple yet effective framework called LDCNet. Our key idea is to use Recurrent Inter-Convolution Differencing (RICD) and Illumination-Affinitive Intra-Convolution Differencing (IAICD) to enhance the nighttime color images and reduce the negative effects of the varying illumination, respectively. RICD explicitly estimates global illumination by differencing two convolutions with different kernels, treating the small-kernel-convolution feature as the center of the large-kernel-convolution feature in a new perspective. IAICD softly alleviates local relative light intensity by differencing a single convolution, where the center is dynamically aggregated based on neighboring pixels and the estimated illumination map in RICD. On both nighttime depth completion and depth estimation tasks, extensive experiments demonstrate the effectiveness of our LDCNet, reaching the state of the art.

翻译：深度补全是从稀疏深度图中恢复密集深度图的任务，通常借助彩色图像完成。现有基于图像引导的方法在白天深度感知自动驾驶基准测试中表现良好，但在能见度低、光照复杂的夜间场景中效果不佳。为解决这些挑战，我们提出一个简单而有效的框架LDCNet。其核心思想是利用循环跨卷积差分（RICD）和光照亲和性内卷积差分（IAICD），分别增强夜间彩色图像并减少变化光照的负面影响。RICD通过差分两个不同核的卷积明确估计全局光照，从新视角将小核卷积特征视为大核卷积特征的中心。IAICD通过差分单个卷积柔和地缓解局部相对光强，其中中心基于相邻像素和RICD中估计的光照图动态聚合。在夜间深度补全和深度估计任务上的大量实验表明，我们的LDCNet达到了当前最优水平。