Multi-Task Deep Networks for Depth-Based 6D Object Pose and Joint Registration in Crowd Scenarios

06/11/2018
by   Juil Sock, et al.
0

In bin-picking scenarios, multiple instances of an object of interest are stacked in a pile randomly, and hence, the instances are inherently subjected to the challenges: severe occlusion, clutter, and similar-looking distractors. Most existing methods are, however, for single isolated object instances, while some recent methods tackle crowd scenarios as post-refinement which accounts multiple object relations. In this paper, we address recovering 6D poses of multiple instances in bin-picking scenarios in depth modality by multi-task learning in deep neural networks. Our architecture jointly learns multiple sub-tasks: 2D detection, depth, and 3D pose estimation of individual objects; and joint registration of multiple objects. For training data generation, depth images of physically plausible object pose configurations are generated by a 3D object model in a physics simulation, which yields diverse occlusion patterns to learn. We adopt a state-of-the-art object detector, and 2D offsets are further estimated via a network to refine misaligned 2D detections. The depth and 3D pose estimator is designed to generate multiple hypotheses per detection. This allows the joint registration network to learn occlusion patterns and remove physically implausible pose hypotheses. We apply our architecture on both synthetic (our own and Sileane dataset) and real (a public Bin-Picking dataset) data, showing that it significantly outperforms state-of-the-art methods by 15-31

READ FULL TEXT

page 2

page 6

page 7

page 8

research
12/23/2015

Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd

Object detection and 6D pose estimation in the crowd (scenes with multip...
research
03/27/2020

Tackling Two Challenges of 6D Object Pose Estimation: Lack of Real Annotated RGB Images and Scalability to Number of Objects

State-of-the-art methods for 6D object pose estimation typically train a...
research
03/11/2019

Instance- and Category-level 6D Object Pose Estimation

6D object pose estimation is an important task that determines the 3D po...
research
01/01/2022

SporeAgent: Reinforced Scene-level Plausibility for Object Pose Refinement

Observational noise, inaccurate segmentation and ambiguity due to symmet...
research
10/11/2019

Scene-level Pose Estimation for Multiple Instances of Densely Packed Objects

This paper introduces key machine learning operations that allow the rea...
research
02/26/2018

Using Curvilinear Features in Focus for Registering a Single Image to a 3D Object

In the context of 2D/3D registration, this paper introduces an approach ...
research
09/28/2021

Affordance Template Registration via Human-in-the-loop Corrections

Affordance Templates (ATs) are a method for parameterizing objects for a...

Please sign up or login with your details

Forgot password? Click here to reset