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

TL;DR

T6D-Direct introduces a transformer-based, real-time, single-stage approach for multi-object 6D pose estimation that achieves competitive accuracy with the fastest inference times on the YCB-Video dataset.

Contribution

It adapts the DETR transformer architecture for direct 6D pose regression, enabling efficient multi-object pose estimation without traditional detection components.

Findings

Achieves real-time inference speed.

Provides pose estimation accuracy comparable to state-of-the-art.

Demonstrates effectiveness on the YCB-Video dataset.

Abstract

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.