SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation
About
Category-level object pose estimation, aiming to predict the 6D pose and 3D size of objects from known categories, typically struggles with large intra-class shape variation. Existing works utilizing mean shapes often fall short of capturing this variation. To address this issue, we present SecondPose, a novel approach integrating object-specific geometric features with semantic category priors from DINOv2. Leveraging the advantage of DINOv2 in providing SE(3)-consistent semantic features, we hierarchically extract two types of SE(3)-invariant geometric features to further encapsulate local-to-global object-specific information. These geometric features are then point-aligned with DINOv2 features to establish a consistent object representation under SE(3) transformations, facilitating the mapping from camera space to the pre-defined canonical space, thus further enhancing pose estimation. Extensive experiments on NOCS-REAL275 demonstrate that SecondPose achieves a 12.4% leap forward over the state-of-the-art. Moreover, on a more complex dataset HouseCat6D which provides photometrically challenging objects, SecondPose still surpasses other competitors by a large margin.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| 6D Pose and Size Estimation | REAL275 | 5°5cm0.636 | 50 | |
| Category-level 6D Object Pose Estimation | NOCS REAL275 | IoU@7550 | 8 | |
| Category-level 6D Object Pose Estimation | ShapeNet-C (test) | Rotation Mean Error (°)45.77 | 7 | |
| 3D Object Pose Estimation | HouseCat6D (test) | Overall IoU 2583.7 | 5 | |
| 6D Object Pose Estimation | HouseCat6D 19 | IoU@7524.9 | 4 |