可学习的差分中心用于夜间深度感知
Learnable Differencing Center for Nighttime Depth Perception
AI总结：
针对夜间深度补全与估计任务，提出LDCNet框架，利用循环卷积间差分和光照亲和卷积内差分增强图像并抑制光照变化，达到最先进性能。
摘要：
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。现有的图像引导方法在白天的自动驾驶深度感知基准上表现良好，但在能见度低、光照复杂的夜间场景中则面临困难。为应对这些挑战，我们提出了一个简单而有效的框架，称为LDCNet。我们的关键思想是使用循环卷积间差分（RICD）和光照亲和卷积内差分（IAICD）来分别增强夜间彩色图像并减少变化光照的负面影响。RICD通过差分两个具有不同核的卷积来显式估计全局光照，从一个新视角将小核卷积特征视为大核卷积特征的中心。IAICD通过差分单个卷积来柔和地缓解局部相对光强度，其中中心基于邻近像素和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，大量实验证明了我们LDCNet的有效性，达到了最先进的性能。
英文摘要：
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.
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。
