.png){kind=icon}
返回
Augmented Autoencoders: Implicit 3D Orientation Learning for 6D Object Detection
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-019-01243-8.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We propose a real-time RGB-based pipeline for object detection and 6D pose estimation. Our novel 3D orientation estimation is based on a variant of the Denoising Autoencoder that is trained on simulated views of a 3D model using Domain Randomization. This so-called Augmented Autoencoder has several advantages over existing methods: It does not require real, pose-annotated training data, generalizes to various test sensors and inherently handles object and view symmetries. Instead of learning an explicit mapping from input images to object poses, it provides an implicit representation of object orientations defined by samples in a latent space. Our pipeline achieves state-of-the-art performance on the T-LESS dataset both in the RGB and RGB-D domain. We also evaluate on the LineMOD dataset where we can compete with other synthetically trained approaches. We further increase performance by correcting 3D orientation estimates to account for perspective errors when the object deviates from the image center and show extended results. Our code is available here https://github.com/DLR-RM/AugmentedAutoencoder.
Keyword:
6D object detection
Pose estimation
Domain randomization
Autoencoder
Synthetic data
Symmetries
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
IF:
9.3
论文数:
3.9K
被引数:
2.8W
机构
引用论文
.png){kind=icon}
Feasibility of Continues Operation of Photovoltaic Systems with Energy Storage during Grid Outages
PREAI
分享收藏Cognitive Predictors of Obsessive–Compulsive Symptoms in Adolescence: A Preliminary Investigation
PREAI
分享收藏
Multi-Criteria Analysis, Evaluation and Modeling of Future Scenario for the Energy Generation Sector — A Case Study能源发电部门未来情景的多标准分析、评估和建模 -- 案例研究
PREAI
分享收藏
查看更多内容