论文标题
深度边缘引导CNNS，稀疏深度升级
Depth Edge Guided CNNs for Sparse Depth Upsampling
论文作者
论文摘要
引导稀疏深度提升采样的目的是在给出对齐的高分辨率颜色图像作为指导时，将不规则采样的稀疏深度图提升。许多神经网络都是为此任务设计的。但是，他们通常会忽略深度和颜色图像之间的结构差异，从而产生明显的伪影，例如纹理副本和在UPS采样深度处的深度模糊。受到归一化卷积操作的启发，我们提出了一个引导的卷积层，以从稀疏和不规则的深度图像中恢复深度，并以深度边缘图像作为指导。我们新颖的引导网络可以防止深度值越过深度边缘以促进上采样。我们进一步设计了一个基于建议的卷积层的卷积网络，以结合不同算法的优势并获得更好的性能。我们进行全面的实验，以验证我们对现实世界和合成室外数据集的方法。我们的方法产生了强劲的结果。它的表现优于虚拟Kitti数据集和Middlebury数据集上的最新方法。它还在不同的3D点密度，各种照明和天气条件下提出了强大的概括能力。
Guided sparse depth upsampling aims to upsample an irregularly sampled sparse depth map when an aligned high-resolution color image is given as guidance. Many neural networks have been designed for this task. However, they often ignore the structural difference between the depth and the color image, resulting in obvious artifacts such as texture copy and depth blur at the upsampling depth. Inspired by the normalized convolution operation, we propose a guided convolutional layer to recover dense depth from sparse and irregular depth image with an depth edge image as guidance. Our novel guided network can prevent the depth value from crossing the depth edge to facilitate upsampling. We further design a convolution network based on proposed convolutional layer to combine the advantages of different algorithms and achieve better performance. We conduct comprehensive experiments to verify our method on real-world indoor and synthetic outdoor datasets. Our method produces strong results. It outperforms state-of-the-art methods on the Virtual KITTI dataset and the Middlebury dataset. It also presents strong generalization capability under different 3D point densities, various lighting and weather conditions.
