CASIA OpenIR  > 精密感知与控制研究中心  > 人工智能与机器学习
Monocular Dense Reconstruction by Depth Estimation Fusion
Chen, Tian1,2; Ding, Wendong1,2; Zhang, Dapeng1,2; Liu, Xilong1,2
Conference NameChinese Control and Decision Conference
Conference Date2018-6-9
Conference PlaceShenyang, China
Contribution Rank1

Dense and accurate reconstruction plays a fundamental role in mobile robot’s environment perception and navigation. It’s also necessary for obstacle avoidance and path planning of mobile robots. We propose a method to incrementally reconstruct the scene from monocular sequence by fusing the depth from geometry computation and gen- erative adversarial networks (GAN) prediction. The depth from geometry triangulation is precise but sparse, while the depth from GAN is dense but unscaled. In this paper, we combine the advantages from two methods with a linear model optimized by graph structure. Experiments showed that our proposed method gives precise dense reconstruction in real time.

KeywordDense Reconstruction, Monocular Depth Estimation, Depth Fusion, Gan
Indexed ByEI
Document Type会议论文
Corresponding AuthorZhang, Dapeng
Affiliation1.Institute of Automation, Chinese Academy of Science, Beijing 100190
2.School of Computer and Control Engineering, University of Chinese Academy of Sciences, Beijing 100190
Recommended Citation
GB/T 7714
Chen, Tian,Ding, Wendong,Zhang, Dapeng,et al. Monocular Dense Reconstruction by Depth Estimation Fusion[C],2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
PID5263415.pdf(837KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chen, Tian]'s Articles
[Ding, Wendong]'s Articles
[Zhang, Dapeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen, Tian]'s Articles
[Ding, Wendong]'s Articles
[Zhang, Dapeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen, Tian]'s Articles
[Ding, Wendong]'s Articles
[Zhang, Dapeng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: PID5263415.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.