RePOSE: Real-Time Iterative Rendering and Refinement for 6D Object Pose Estimation

04/01/2021
by   Shun Iwase, et al.
3

The use of iterative pose refinement is a critical processing step for 6D object pose estimation, and its performance depends greatly on one's choice of image representation. Image representations learned via deep convolutional neural networks (CNN) are currently the method of choice as they are able to robustly encode object keypoint locations. However, CNN-based image representations are computational expensive to use for iterative pose refinement, as they require that image features are extracted using a deep network, once for the input image and multiple times for rendered images during the refinement process. Instead of using a CNN to extract image features from a rendered RGB image, we propose to directly render a deep feature image. We call this deep texture rendering, where a shallow multi-layer perceptron is used to directly regress a view invariant image representation of an object. Using an estimate of the pose and deep texture rendering, our system can render an image representation in under 1ms. This image representation is optimized such that it makes it easier to perform nonlinear 6D pose estimation by adding a differentiable Levenberg-Marquardt optimization network and back-propagating the 6D pose alignment error. We call our method, RePOSE, a Real-time Iterative Rendering and Refinement algorithm for 6D POSE estimation. RePOSE runs at 71 FPS and achieves state-of-the-art accuracy of 51.6 dataset - a 4.1 performance on the YCB-Video dataset with a much faster runtime than the other pose refinement methods.

READ FULL TEXT

page 1

page 3

page 5

page 7

research
08/03/2018

Real-Time Object Pose Estimation with Pose Interpreter Networks

In this work, we introduce pose interpreter networks for 6-DoF object po...
research
04/26/2022

Coupled Iterative Refinement for 6D Multi-Object Pose Estimation

We address the task of 6D multi-object pose: given a set of known 3D obj...
research
11/17/2019

Fast 3D Pose Refinement with RGB Images

Pose estimation is a vital step in many robotics and perception tasks su...
research
11/24/2017

Real-Time Seamless Single Shot 6D Object Pose Prediction

We propose a single-shot approach for simultaneously detecting an object...
research
12/04/2018

Estimating 6D Pose From Localizing Designated Surface Keypoints

In this paper, we present an accurate yet effective solution for 6D pose...
research
07/17/2020

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

We present a novel 3D pose refinement approach based on differentiable r...
research
11/26/2020

Handling Object Symmetries in CNN-based Pose Estimation

In this paper we investigate the problems that Convolutional Neural Netw...

Please sign up or login with your details

Forgot password? Click here to reset