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

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. 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.

Code available at: https://github.com/DLR-RM/AugmentedAutoencoder

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects
• PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes
• Real-Time Seamless Single Shot 6D Object Pose Prediction

Cited by in corpus (1)

• Iterative Optimisation with an Innovation CNN for Pose Refinement