论文标题
selfdeco：在具有挑战性的室内环境中，自我监督的单眼深度完成
SelfDeco: Self-Supervised Monocular Depth Completion in Challenging Indoor Environments
论文作者
论文摘要
我们提出了一种新颖的算法，用于自制的单眼深度完成。我们的方法是基于训练神经网络，该神经网络只需要稀疏的深度测量和相应的单眼视频序列而没有密集的深度标签。我们的自我监督算法设计用于具有无纹理区域，光泽和透明的表面，非陆层表面，使人，更长和多样化的深度范围和场景被复杂的自我动物捕获的范围，使人越来越长，更长，更多样化的人。我们的新型建筑利用了稀疏卷积块的两个深层堆栈来提取稀疏的深度特征和像素自动卷积来融合图像和深度特征。我们与NYUV2，KITTI和NAVERLABS室内数据集中的现有方法进行了比较，并观察到根均值平方误差（RMSE）减少的5-34％。
We present a novel algorithm for self-supervised monocular depth completion. Our approach is based on training a neural network that requires only sparse depth measurements and corresponding monocular video sequences without dense depth labels. Our self-supervised algorithm is designed for challenging indoor environments with textureless regions, glossy and transparent surface, non-Lambertian surfaces, moving people, longer and diverse depth ranges and scenes captured by complex ego-motions. Our novel architecture leverages both deep stacks of sparse convolution blocks to extract sparse depth features and pixel-adaptive convolutions to fuse image and depth features. We compare with existing approaches in NYUv2, KITTI, and NAVERLABS indoor datasets, and observe 5-34 % improvements in root-means-square error (RMSE) reduction.
