MFOS: Model-Free & One-Shot Object Pose Estimation

TL;DR

This paper introduces a transformer-based, model-free one-shot object pose estimation method that generalizes to unseen objects without requiring 3D data, achieving state-of-the-art results on LINEMOD.

Contribution

It presents a novel transformer-based approach for one-shot pose estimation that does not depend on object-specific models or 3D data, enhancing generalization and scalability.

Findings

Achieves state-of-the-art one-shot performance on LINEMOD

Operates in a single forward pass without object-specific training

Provides insights through extensive ablations

Abstract

Existing learning-based methods for object pose estimation in RGB images are mostly model-specific or category based. They lack the capability to generalize to new object categories at test time, hence severely hindering their practicability and scalability. Notably, recent attempts have been made to solve this issue, but they still require accurate 3D data of the object surface at both train and test time. In this paper, we introduce a novel approach that can estimate in a single forward pass the pose of objects never seen during training, given minimum input. In contrast to existing state-of-the-art approaches, which rely on task-specific modules, our proposed model is entirely based on a transformer architecture, which can benefit from recently proposed 3D-geometry general pretraining. We conduct extensive experiments and report state-of-the-art one-shot performance on the challenging LINEMOD benchmark. Finally, extensive ablations allow us to determine good practices with this relatively new type of architecture in the field.