DeepAI AI Chat
Log In Sign Up

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

by   Ameni Trabelsi, et al.

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.


page 3

page 10

page 11

page 12

page 13


Spatial Attention Improves Iterative 6D Object Pose Estimation

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

Iterative Optimisation with an Innovation CNN for Pose Refinement

Object pose estimation from a single RGB image is a challenging problem ...

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

Object recognition and 6DoF pose estimation are quite challenging tasks ...

ChiNet: Deep Recurrent Convolutional Learning for Multimodal Spacecraft Pose Estimation

This paper presents an innovative deep learning pipeline which estimates...

Towards Two-view 6D Object Pose Estimation: A Comparative Study on Fusion Strategy

Current RGB-based 6D object pose estimation methods have achieved notice...

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...

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...