Towards Domain-agnostic Depth Completion

doi:10.1007/s11633-024-1494-4

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	Towards Domain-agnostic Depth Completion
	Guangkai Xu 1; Wei Yin 2; Jianming Zhang 3; Oliver Wang 3; Simon Niklaus 3; Simon Chen 3; Jia-Wang Bian 4
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2024
卷号	21 期号:4 页码:652-669
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 high quality depth capture on a mobile device.
关键词	Monocular depth estimation depth completion zero-shot generalization scene reconstruction neural network
DOI	10.1007/s11633-024-1494-4
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58565
专题	学术期刊_Machine Intelligence Research
作者单位	1.Zhejiang University, Hangzhou 310058, China 2.DaJiang Technology, Shenzhen 518057, China 3.Adobe Research, California 95110, USA 4.University of Oxford, Oxford OX1 2JD, UK
推荐引用方式 GB/T 7714	Guangkai Xu, Wei Yin, Jianming Zhang,et al. Towards Domain-agnostic Depth Completion[J]. Machine Intelligence Research,2024,21(4):652-669.
APA	Guangkai Xu., Wei Yin., Jianming Zhang., Oliver Wang.,Simon Niklaus.,...& Jia-Wang Bian.(2024).Towards Domain-agnostic Depth Completion.Machine Intelligence Research,21(4),652-669.
MLA	Guangkai Xu,et al."Towards Domain-agnostic Depth Completion".Machine Intelligence Research 21.4(2024):652-669.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2023-03-031.pdf（17196KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载