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

Author: A. Amini, A. S. Periyasamy, S. Behnke
Journal: DAGM GCPR 2021: Pattern Recognition
Year: 2021

Citation information

A. Amini, A. S. Periyasamy, S. Behnke,
DAGM GCPR 2021: Pattern Recognition,
2021,
530–544,
Springer, Cham,
https://doi.org/10.1007/978-3-030-92659-5_34

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 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.