English

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

Computer Vision and Pattern Recognition 2023-07-24 v1

Abstract

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 and an improved variant of the YOLOPose model. 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. We analyze the role of object queries in our architecture and reveal that the object queries specialize in detecting objects in specific image regions. Furthermore, we quantify the accuracy trade-off of using datasets of smaller sizes to train our model.

Keywords

Cite

@article{arxiv.2307.11550,
  title  = {YOLOPose V2: Understanding and Improving Transformer-based 6D Pose Estimation},
  author = {Arul Selvam Periyasamy and Arash Amini and Vladimir Tsaturyan and Sven Behnke},
  journal= {arXiv preprint arXiv:2307.11550},
  year   = {2023}
}

Comments

Robotics and Autonomous Systems Journal, Elsevier, to appear 2023. arXiv admin note: substantial text overlap with arXiv:2205.02536

R2 v1 2026-06-28T11:36:56.070Z