Depth completion aims at inferring a dense depth image from sparse depth measurement since glossy, transparent or distant surface cannot be scanned properly by the sensor. Most of existing methods directly interpolate the missing depth measurements based on pixel-wise image content and the corresponding neighboring depth values. Consequently, this leads to blurred boundaries or inaccurate structure of object. To address these problems, we propose a novel self-guided instance-aware network (SG-IANet) that: (1) utilize self-guided mechanism to extract instance-level features that is needed for depth restoration, (2) exploit the geometric and context information into network learning to conform to the underlying constraints for edge clarity and structure consistency, (3) regularize the depth estimation and mitigate the impact of noise by instance-aware learning, and (4) train with synthetic data only by domain randomization to bridge the reality gap. Extensive experiments on synthetic and real world dataset demonstrate that our proposed method outperforms previous works. Further ablation studies give more insights into the proposed method and demonstrate the generalization capability of our model.

翻译：深度完成的目的是从由于光滑、透明或遥远的表面无法由传感器适当扫描而稀薄的深度测量中推断出一个深厚的深度图象,因为光滑、透明或遥远的表面无法由传感器适当扫描; 多数现有方法直接对根据像素图像内容和相应的相邻深度值进行的缺失深度测量进行内插,从而导致物体的界限模糊或不准确; 为了解决这些问题,我们提议建立一个全新的自导实例认知网络(SG-IANet), 以:(1) 利用自导机制提取深度恢复所需的实例级特征;(2) 利用几何和背景信息进行网络学习,以符合边缘清晰度和结构一致性的基本限制;(3) 规范深度估计,并通过实例认知学习减轻噪音的影响;(4) 仅通过区域随机化进行合成数据培训,以弥合现实差距; 对合成和真实世界数据集进行广泛的实验,表明我们拟议的方法比以前的工程要好; 进一步进行对比研究,以更深入地了解拟议方法,并展示我们模型的总体能力。