| |||||||
ShanghaiTech University Knowledge Management System
Learning to refine depth for robust stereo estimation | |
2018-02 | |
发表期刊 | PATTERN RECOGNITION (IF:7.5[JCR-2023],7.6[5-Year]) |
ISSN | 0031-3203 |
卷号 | 74页码:122-133 |
发表状态 | 已发表 |
DOI | 10.1016/j.patcog.2017.07.027 |
摘要 | Traditional depth estimation from stereo images is usually formulated as a patch-matching problem, which requires post-processing stages to impose smoothness and handle depth discontinuities and occlusions. While recent deep network approaches directly learn a regressor for the entire disparity map, they still suffer from large errors near the depth discontinuities. In this paper, we propose a novel method to refine the disparity maps generated by deep regression networks. Instead of relying on ad hoc post processing, we learn a unified deep network model that predicts a confidence map and the disparity gradients from the learned feature representation in regression networks. We integrate the initial disparity estimation, the confidence map and the disparity gradients into a continuous Markov Random Field (MRF) for depth refinement, which is capable of representing rich surface structures. Our disparity MRF model can be solved via efficient global optimization in a closed form. We evaluate our approach on both synthetic and real-world datasets, and the results show it achieves the state-of-art performance and produces more structure-preserving disparity maps with smaller errors in the neighborhood of depth boundaries. (C) 2017 Elsevier Ltd. All rights reserved. |
关键词 | Stereo matching Confidence measure Convolutional neural network |
收录类别 | SCI ; SCIE |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61571026] |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000417547800010 |
出版者 | ELSEVIER SCI LTD |
WOS关键词 | ACCURATE |
原始文献类型 | Article |
引用统计 | 正在获取...
|
文献类型 | 期刊论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/14295 |
专题 | 信息科学与技术学院_PI研究组_何旭明组 |
通讯作者 | Zhang, Hong |
作者单位 | 1.Beihang Univ, Image Res Ctr, Xueyuan Rd, Beijing 100191, Peoples R China 2.Natl ICT Australia, Comp Vis Grp, Locked Bag 8001, Canberra, ACT 2601, Australia 3.Australia Natl Univ, Canberra, ACT, Australia 4.ShanghaiTech Univ, Shanghai, Peoples R China |
推荐引用方式 GB/T 7714 | Cheng, Feiyang,He, Xuming,Zhang, Hong. Learning to refine depth for robust stereo estimation[J]. PATTERN RECOGNITION,2018,74:122-133. |
APA | Cheng, Feiyang,He, Xuming,&Zhang, Hong.(2018).Learning to refine depth for robust stereo estimation.PATTERN RECOGNITION,74,122-133. |
MLA | Cheng, Feiyang,et al."Learning to refine depth for robust stereo estimation".PATTERN RECOGNITION 74(2018):122-133. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
修改评论
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。