papers AI Learner
The Github is limit! Click to go to the new site.

Implicit 3D Orientation Learning for 6D Object Detection from RGB Images

2019-02-04
Martin Sundermeyer, Zoltan-Csaba Marton, Maximilian Durner, Manuel Brucker, Rudolph Triebel

Abstract

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. Experiments on the T-LESS and LineMOD datasets show that our method outperforms similar model-based approaches and competes with state-of-the art approaches that require real pose-annotated images.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1902.01275

PDF

http://arxiv.org/pdf/1902.01275


Similar Posts

Comments