Towards Domain-agnostic Depth Completion  

作　　者：Guangkai Xu Wei Yin Jianming Zhang Oliver Wang Simon Niklaus Simon Chen Jia-Wang Bian 

机构地区：[1]Zhejiang University,Hangzhou 310058,China [2]DaJiang Technology,Shenzhen 518057,China [3]Adobe Research,California 95110,USA [4]University of Oxford,Oxford OX12JD,UK

出　　处：《Machine Intelligence Research》2024年第4期652-669,共18页机器智能研究（英文版）

摘　　要：Existing depth completion methods are often targeted at a specific sparse depth type and generalize poorly across task domains.We present a method to complete sparse/semi-dense,noisy,and potentially low-resolution depth maps obtained by various range sensors,including those in modern mobile phones,or by multi-view reconstruction algorithms.Our method leverages a data-driven prior in the form of a single image depth prediction network trained on large-scale datasets,the output of which is used as an input to our model.We propose an effective training scheme where we simulate various sparsity patterns in typical task domains.In addition,we design two new benchmarks to evaluate the generalizability and robustness of depth completion methods.Our simple method shows superior cross-domain generalization ability against state-of-the-art depth completion methods,introducing a practical solution to highqualitydepthcapture onamobile device.

关 键 词：Monocular depth estimation depth completion zero-shot generalization scene reconstruction neural network. 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]