arrow
返回

Domain-Translated 3D Object Pose Estimation

delete2020-01-01
delete14
PRE
AI
C
Christos Papaioannidis *
V
Vasileios Mygdalis
I
Ioannis Pitas
DOI:10.1109/TIP.2020.3025447delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Synthetic 3D object models have been proven crucial in object pose estimation, as they are utilized to generate a huge number of accurately annotated data. The object pose estimation problem is usually solved for images originating from the real data domain by employing synthetic images for training data enrichment, without fully exploiting the fact that synthetic and real images may have different data distributions. In this work, we argue that 3D object pose estimation problem is easier to solve for images originating from the synthetic domain, rather than the real data domain. To this end, we propose a 3D object pose estimation framework consisting of a two-step process, where a novel pose-oriented image-to-image translation step is first employed to translate noisy real images to clean synthetic ones and then, a 3D object pose estimation method is applied on the translated synthetic images to finally predict the 3D object poses. A novel pose-oriented objective function is employed for training the image-to-image translation network, which enforces that pose-related object image characteristics are preserved in the translated images. As a result, the pose estimation network does not require real data for training purposes. Experimental evaluation has shown that the proposed framework greatly improves the 3D object pose estimation performance, when compared to state-of-the-art methods.
Keyword:
Three-dimensional displays
Pose estimation
Feature extraction
Training
Task analysis
Two dimensional displays
Training data
3D object pose estimation
image-to-image translation
domain-translated
synthetic data
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Transactions on Image Processing 封面图
IEEE Transactions on Image Processing
IF:
13.7
论文数:
1.0W
被引数:
8.4W

机构

A
aristotle university of thessaloniki
学者数:
2.6W
论文数: 2.0W
被引数: 19
引用论文

引用论文

err分享
err收藏
Public goods games in populations with fluctuating size
err2018-05-01
err0
errOAAI
errAlex McAvoy; Nicolas Fraiman; Christoph Hauert; John Wakeley; Martin A. Nowak
err分享
err收藏
Jets, stickiness, and anomalous transport
err2002-04-04
err0
errOAAI
errXavier Leoncini; George M. Zaslavsky
err分享
err收藏
An increased number of CD40-high monocytes in patients with Crohn's disease
err2000-06-01
err0
PREAI
errNaoko Sawada-Hase; Tatsuya Kiyohara; Jun-ichiro Miyagawa; Harumi Ueyama; Hiroyuki Nishibayashi; Yoko Murayama; Takeshi Kashihara; Masanori Nakahara; Yoshiji Miyazaki; Shuji Kanayama; Riichiro Nezu; Yasuhisa Shinomura; Yuji Matsuzawa
err分享
err收藏
学者 查看更多内容