6D pose estimation is the task of predicting the translation and orientation of objects in a given input image, which is a crucial prerequisite for many robotics and augmented reality applications. Lately, the Transformer Network architecture, equipped with a multi-head self-attention mechanism, is emerging to achieve state-of-the-art results in many computer vision tasks. DETR, a Transformer-based model, formulated object detection as a set prediction problem and achieved impressive results without standard components like region of interest pooling, non-maximal suppression, and bounding box proposals. In this work, we propose T6D-Direct, a real-time single-stage direct method with a transformer-based architecture built on DETR to perform 6D multi-object pose direct estimation. We evaluate the performance of our method on the YCB-Video dataset. Our method achieves the fastest inference time, and the pose estimation accuracy is comparable to state-of-the-art methods.
@article{arxiv.2109.10948,
title = {T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression},
author = {Arash Amini and Arul Selvam Periyasamy and Sven Behnke},
journal= {arXiv preprint arXiv:2109.10948},
year = {2021}
}
Comments
Accepted for DAGM German Conference on Pattern Recognition (GCPR), Bonn, Germany, September 2021