A Novel Pose Proposal Network and Refinement Pipeline for Better Object Pose Estimation

04/11/2020
by   Ameni Trabelsi, et al.
5

In this paper, we present a novel deep learning pipeline for 6D object pose estimation and refinement from RGB inputs. The first component of the pipeline leverages a region proposal framework to estimate multi-class single-shot 6D object poses directly from an RGB image and through a CNN-based encoder multi-decoders network. The second component, a multi-attentional pose refinement network (MARN), iteratively refines the estimated pose. MARN takes advantage of both visual and flow features to learn a relative transformation between an initially predicted pose and a target pose. MARN is further augmented by a spatial multi-attention block that emphasizes objects' discriminative feature parts. Experiments on three benchmarks for 6D pose estimation show that the proposed pipeline outperforms state-of-the-art RGB-based methods with competitive runtime performance.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 10

page 11

page 12

page 13

01/05/2021

Spatial Attention Improves Iterative 6D Object Pose Estimation

The task of estimating the 6D pose of an object from RGB images can be b...
01/22/2021

Iterative Optimisation with an Innovation CNN for Pose Refinement

Object pose estimation from a single RGB image is a challenging problem ...
11/17/2019

Fast 3D Pose Refinement with RGB Images

Pose estimation is a vital step in many robotics and perception tasks su...
02/28/2018

Deep-6DPose: Recovering 6D Object Pose from a Single RGB Image

Detecting objects and their 6D poses from only RGB images is an importan...
12/05/2017

The Best of Both Worlds: Learning Geometry-based 6D Object Pose Estimation

We address the task of estimating the 6D pose of known rigid objects, fr...
11/27/2020

Towards real-time object recognition and pose estimation in point clouds

Object recognition and 6DoF pose estimation are quite challenging tasks ...
01/31/2022

Combining Local and Global Pose Estimation for Precise Tracking of Similar Objects

In this paper, we present a multi-object 6D detection and tracking pipel...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.