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