ZS6D: Zero-shot 6D Object Pose Estimation using Vision Transformers

TL;DR

This paper introduces ZS6D, a zero-shot 6D object pose estimation method using pre-trained Vision Transformers, eliminating the need for task-specific fine-tuning and achieving superior results on multiple datasets.

Contribution

ZS6D leverages pre-trained Vision Transformers for zero-shot 6D pose estimation, avoiding expensive training and fine-tuning procedures of prior methods.

Findings

Improves Average Recall on LMO, YCBV, and TLESS datasets.

Outperforms state-of-the-art methods without task-specific fine-tuning.

Uses ViT descriptors for robust template matching and pose estimation.

Abstract

As robotic systems increasingly encounter complex and unconstrained real-world scenarios, there is a demand to recognize diverse objects. The state-of-the-art 6D object pose estimation methods rely on object-specific training and therefore do not generalize to unseen objects. Recent novel object pose estimation methods are solving this issue using task-specific fine-tuned CNNs for deep template matching. This adaptation for pose estimation still requires expensive data rendering and training procedures. MegaPose for example is trained on a dataset consisting of two million images showing 20,000 different objects to reach such generalization capabilities. To overcome this shortcoming we introduce ZS6D, for zero-shot novel object 6D pose estimation. Visual descriptors, extracted using pre-trained Vision Transformers (ViT), are used for matching rendered templates against query images of objects and for establishing local correspondences. These local correspondences enable deriving geometric correspondences and are used for estimating the object's 6D pose with RANSAC-based PnP. This approach showcases that the image descriptors extracted by pre-trained ViTs are well-suited to achieve a notable improvement over two state-of-the-art novel object 6D pose estimation methods, without the need for task-specific fine-tuning. Experiments are performed on LMO, YCBV, and TLESS. In comparison to one of the two methods we improve the Average Recall on all three datasets and compared to the second method we improve on two datasets.