Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Images

In this paper, we present a generalizable model-free 6-DoF object pose estimator called Gen6D. Existing generalizable pose estimators either need the high-quality object models or require additional depth maps or object masks in test time, which significantly limits their application scope. In contrast, our pose estimator only requires some posed images of the unseen object and is able to accurately predict poses of the object in arbitrary environments. Gen6D consists of an object detector, a viewpoint selector and a pose refiner, all of which do not require the 3D object model and can generalize to unseen objects. Experiments show that Gen6D achieves state-of-the-art results on two model-free datasets: the MOPED dataset and a new GenMOP dataset. In addition, on the LINEMOD dataset, Gen6D achieves competitive results compared with instance-specific pose estimators. Project page: https://liuyuan-pal.github.io/Gen6D/.

Automated summary

This paper presents Gen6D, a generalizable model-free 6-DoF object pose estimator. Unlike existing methods, Gen6D does not require high-quality object models, depth maps, or object masks during testing. Experimental results demonstrate that Gen6D achieves state-of-the-art performance on model-free datasets and competitive results on the LINEMOD dataset compared to instance-specific pose estimators.