Treffer: 基于边界预测辅助的稀疏深度图像修复.

Depth images completion aims to recover dense depth images from sparse depth images. However, the depth images restored by many current depth completion algorithms often suffer from problems such as missing detail structures, depth discontinuities and blurred boundaries. To address these problems, this paper proposes a sparse depth completion method based on boundary prediction assistance, in which depth image completion is the main task and boundary prediction is the auxiliary task. A cross-guidance module is proposed to realize information interaction between the main task and the auxiliary task and provide effective boundary constraint for the main completion task. Moreover, an intermediate feature extraction module is used to extract multiple perceptual field features for scene context learning. In this paper, a series of experiments were conducted on the indoor dataset NYUv2 and the outdoor dataset KITTI, the experimental results prove the effectiveness of the proposed algorithms and modules, and it is superior to some mainstream depth completion methods in qualitative and quantitative comparison. [ABSTRACT FROM AUTHOR]

深度图像修复旨在从稀疏深度图像中恢复出稠密的深度图像, 然而目前许多深度修复 算法所修复出的深度图像往往存在细节结构缺失、深度不连续和边界模糊等问题。为此, 文章提出 一个基于边界预测辅助的稀疏深度修复方法: 以深度图像修复为主任务、边界预测为辅助任务, 通过 建立交叉引导模块实现主任务与辅助任务间的信息交互, 通过辅助任务的学习为修复主任务提供有 效的边界约束, 同时由网络的中间特征提取模块进行多感受野特征的提取和学习, 以更好地获取上 下文信息。利用室内数据集 NYUv2 和户外数据集 KITTI 进行一系列实验, 定性与定量的结果表明, 该方法是有效的, 并优于一些主流的深度修复方法。 [ABSTRACT FROM AUTHOR]