In the current state of 6D pose estimation, top-performing techniques depend
on complex intermediate correspondences, specialized architectures, and
non-end-to-end algorithms. In contrast, our research reframes the problem as a
straightforward regression task by exploring the capabilities of Vision
Transformers for direct 6D pose estimation through a tailored use of
classification tokens. We also introduce a simple method for determining pose
confidence, which can be readily integrated into most 6D pose estimation
frameworks. This involves modifying the transformer architecture by decreasing
the number of query elements based on the network's assessment of the scene
complexity. Our method that we call Pose Vision Transformer or PViT-6D provides
the benefits of simple implementation and being end-to-end learnable while
outperforming current state-of-the-art methods by +0.3% ADD(-S) on
Linemod-Occlusion and +2.7% ADD(-S) on the YCB-V dataset. Moreover, our method
enhances both the model's interpretability and the reliability of its
performance during inference.

我们的研究将 6D 姿态估计问题转化为直接的回归任务，利用 Vision Transformers 的能力进行探索，通过对分类标记的定制使用来进行姿态估计。我们还引入了一种简单的方法来确定姿态的置信度，这可以很容易地集成到大多数 6D 姿态估计框架中。我们的方法 PViT-6D 在实现简单和端到端可学习的同时，表现优于当前最先进方法，在 Linemod-Occlusion 数据集上提高 0.3% ADD (-S)，在 YCB-V 数据集上提高 2.7% ADD (-S)。此外，我们的方法提高了模型的可解释性和推理性能的可靠性。