Knowledge Commons of Institute of Automation,CAS
Learning adversarial point-wise domain alignment for stereo matching | |
Zhang, Chenghao1,2; Meng, Gaofeng1,2,3; Xu, Richard Yi Da4; Xiang, Shiming1,2; Pan, Chunhong1 | |
发表期刊 | NEUROCOMPUTING |
ISSN | 0925-2312 |
2022-06-28 | |
卷号 | 491页码:564-574 |
摘要 | The state-of-the-art stereo matching models trained on synthetic datasets have difficulty in generalizing to real-world datasets. One major reason is that illumination and texture in the real world are hard to be simulated, resulting in big differences between synthetic and real-world data. In this study, instead of narrowing the image-level appearance difference, we focus on aligning both data domains in feature space in an unsupervised manner and propose an end-to-end domain alignment stereo network (DAStereo). A domain alignment module (DAM) is introduced by learning a point-wise linear transformation. We demonstrate that DAM can maintain sufficient alignment capacity with fewer parameters than the globally nonlinear mapping. To explicitly promote the point-wise domain alignment, adversarial learning is further introduced using a cost volume discriminator in a hybrid training manner. Experimental results show that DAStereo outperforms the state-of-the-art unsupervised and adaptive methods and even achieves comparable performance to some supervised methods. (C) 2021 Elsevier B.V. All rights reserved. |
关键词 | Stereo Matching Domain adaptation Point-wise linear transformation Adversarial learning |
DOI | 10.1016/j.neucom.2021.12.034 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key Research and Development Program of China[2018AAA0100400] ; National Natural Science Foundation of China[61802407] ; National Natural Science Foundation of China[61976208] ; National Natural Science Foundation of China[62071466] |
项目资助者 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000830181200013 |
出版者 | ELSEVIER |
七大方向——子方向分类 | 三维视觉 |
国重实验室规划方向分类 | 视觉信息处理 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/49843 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Meng, Gaofeng |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, HK Inst Sci & Innovat, Beijing, Peoples R China 4.Univ Technol Sydney UTS, Fac Engn & Informat Technol, Ultimo, NSW 2007, Australia |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhang, Chenghao,Meng, Gaofeng,Xu, Richard Yi Da,et al. Learning adversarial point-wise domain alignment for stereo matching[J]. NEUROCOMPUTING,2022,491:564-574. |
APA | Zhang, Chenghao,Meng, Gaofeng,Xu, Richard Yi Da,Xiang, Shiming,&Pan, Chunhong.(2022).Learning adversarial point-wise domain alignment for stereo matching.NEUROCOMPUTING,491,564-574. |
MLA | Zhang, Chenghao,et al."Learning adversarial point-wise domain alignment for stereo matching".NEUROCOMPUTING 491(2022):564-574. |
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 | ||
论文序号4_NC.pdf(3885KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论