YOLOPose: Transformer-based Multi-Object 6D Pose Estimation using Keypoint Regression

05/05/2022
by   Arash Amini, et al.
63

6D object pose estimation is a crucial prerequisite for autonomous robot manipulation applications. The state-of-the-art models for pose estimation are convolutional neural network (CNN)-based. Lately, Transformers, an architecture originally proposed for natural language processing, is achieving state-of-the-art results in many computer vision tasks as well. Equipped with the multi-head self-attention mechanism, Transformers enable simple single-stage end-to-end architectures for learning object detection and 6D object pose estimation jointly. In this work, we propose YOLOPose (short form for You Only Look Once Pose estimation), a Transformer-based multi-object 6D pose estimation method based on keypoint regression. In contrast to the standard heatmaps for predicting keypoints in an image, we directly regress the keypoints. Additionally, we employ a learnable orientation estimation module to predict the orientation from the keypoints. Along with a separate translation estimation module, our model is end-to-end differentiable. Our method is suitable for real-time applications and achieves results comparable to state-of-the-art methods.

READ FULL TEXT

page 8

page 11

page 12

research
07/21/2023

YOLOPose V2: Understanding and Improving Transformer-based 6D Pose Estimation

6D object pose estimation is a crucial prerequisite for autonomous robot...
research
09/22/2021

T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression

6D pose estimation is the task of predicting the translation and orienta...
research
03/22/2021

End-to-End Trainable Multi-Instance Pose Estimation with Transformers

We propose a new end-to-end trainable approach for multi-instance pose e...
research
12/09/2021

PE-former: Pose Estimation Transformer

Vision transformer architectures have been demonstrated to work very eff...
research
03/24/2022

RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers

We propose a transformer-based neural network architecture for multi-obj...
research
12/12/2016

PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning

State-of-the-art computer vision algorithms often achieve efficiency by ...
research
11/21/2022

Simultaneous Multiple Object Detection and Pose Estimation using 3D Model Infusion with Monocular Vision

Multiple object detection and pose estimation are vital computer vision ...

Please sign up or login with your details

Forgot password? Click here to reset